claude-007-agents
🤖 A unified AI agent orchestration system featuring 10's of specialized agents across 14 categories for modern software development. Built with advanced coordination intelligence, resilience engineering, and structured logging capabilities.
Stars: 159
Claude Code Agents is an open-source AI agent system designed to enhance development workflows by providing specialized AI agents for orchestration, resilience engineering, and organizational memory. These agents offer specialized expertise across technologies, AI system with organizational memory, and an agent orchestration system. The system includes features such as engineering excellence by design, advanced orchestration system, Task Master integration, live MCP integrations, professional-grade workflows, and organizational intelligence. It is suitable for solo developers, small teams, enterprise teams, and open-source projects. The system requires a one-time bootstrap setup for each project to analyze the tech stack, select optimal agents, create configuration files, set up Task Master integration, and validate system readiness.
README:
Enhance your development workflow with specialized AI agents that help deliver quality code through orchestration, resilience engineering, and organizational memory.
Open-source AI agents for enhanced development workflows
Reduce context switching between documentation, Stack Overflow, and your IDE. Get access to specialized agents covering major frameworks, languages, and domains.
# Instead of spending hours researching...
claude "Build a resilient authentication system with circuit breakers and structured logging"
# → @rails-expert + @resilience-engineer + @security-specialist work in perfect coordinationThese agents can remember and learn from projects when configured with Basic Memory MCP, helping build institutional knowledge over time.
- Pattern Reuse: "Use patterns from previous authentication implementations"
- Context Building: "Reference similar microservice architectures we've built"
- Knowledge Evolution: "Update our React component patterns based on this success"
The system includes coordination features that can help with agent selection and workflow management for complex tasks.
# Just describe what you want - the system handles everything automatically:
claude "Build an e-commerce platform"
# → Vibe Coding Coordinator: 15-20 minute preparation phase, analyzes requirements
# → Exponential Planner: Strategic planning with capability scaling awareness
# → Parallel Coordinator: Coordinates (@react-expert + @rails-expert + @payment-specialist + @security-specialist)
# → Session Manager: Maintains context across extended development sessions
# → Safety Specialists: Pre-deployment validation and architectural analysis⚡ ONE-TIME SETUP: Every project needs bootstrapping before using Claude 007 Agents!
# After installing agents, bootstrap each project once:
claude "Use @bootstrap-orchestrator to analyze and setup this project"Why Bootstrap?
- 🔍 Analyzes your tech stack and selects optimal agents
- ⚙️ Creates proper CLAUDE.md configuration with commit attribution
- 🎯 Sets up project-specific agent selection and workflows
- 📋 Configures Task Master integration for codebase-aware development
- ✅ Validates complete system readiness
Skip this step and agents won't work properly in your project!
Every agent prioritizes production-grade quality:
- ⚡ Fault Tolerance: Circuit breakers, retry mechanisms, graceful degradation
- 📊 Structured Logging: JSON logging with contextual information
- 🔄 Self-Healing: Automatic recovery patterns
- 🛡️ Automated Quality: Trunk.io integration for linting and security
Built on insights from Anthropic's "Code with Claude" conference:
- Vibe Coding Coordinator: 15-20 minute preparation phases for autonomous development
- Exponential Planner: Strategic planning with AI capability doubling awareness (7-month cycles)
- Session Manager: Resumable workflows with context preservation across extended sessions
- Parallel Coordinator: Multi-agent execution with coordinated tool calling
- Safety Specialists: Pre-deployment testing, architectural analysis, and risk management
- Sequential Thinking: Complex multi-step reasoning with adaptive planning and course correction
Revolutionary codebase-aware autonomous development ecosystem:
- Codebase-Aware Intelligence: Tasks generated with deep understanding of existing code architecture and patterns
- Bridge Agent Architecture: 5 specialized Task Master agents seamlessly integrated with Claude 007's 112 agents
- Multi-Model AI Configuration: Support for Claude, Gemini, Perplexity, OpenAI, and more
- Template Intelligence: Smart generation of MCP configs, environment files, and PRD templates
- Autonomous Development: 30-40% development time reduction with quality assurance
Direct access to live systems and real-time data:
- GitHub MCP: Live repository operations and PR management
- Task Master MCP: Project management with complexity analysis and codebase awareness
- Context7 MCP: Up-to-date library documentation
- Basic Memory MCP: Persistent organizational knowledge
- Sequential Thinking MCP: Complex reasoning with adaptive planning and course correction
- Vibe Coding: 15-20 minute autonomous development preparation phases
- Parallel Execution: Coordinated multi-agent development with tool call batching
- Exponential Planning: Long-term development planning with AI capability scaling awareness
- Sequential Reasoning: Multi-step problem analysis with adaptive strategy revision
- Safety Validation: Pre-deployment testing and architectural safety analysis
- Dynamic Permissions: Real-time permission management with risk-based escalation
- Automatic Commit Attribution: Every commit traces back to contributing agents
- Quality Gates: Pre-commit hooks with comprehensive linting
- Cross-Project Learning: Patterns and knowledge shared across all projects
- Decision History: Track architectural decisions and their outcomes
- Performance Analytics: Agent effectiveness measurement and optimization
- Knowledge Graphs: Dynamic project understanding with real-time updates
| Team Size | Use Case | Key Benefits |
|---|---|---|
| Solo Developers | Full-stack development, learning new technologies | Instant expertise, quality assurance, best practices |
| Small Teams (2-10) | Startup MVPs, rapid prototyping, scaling challenges | Coordinated development, knowledge sharing, quality consistency |
| Enterprise Teams | Complex systems, compliance, technical debt | Orchestrated workflows, organizational memory, standardized practices |
| Open Source | Community projects, documentation, code reviews | Automated quality, contributor onboarding, pattern consistency |
IMPORTANT: You must bootstrap the agent system once for every new repo/project before using Claude 007 Agents.
# 1. Clone the system
git clone https://github.com/avivl/claude-007-agents.git
cd claude-007-agents
# 2. Copy to your project (any project)
cp -r .claude/agents /path/to/your/project/.claude/
cp agents.json /path/to/your/project/
# 3. BOOTSTRAP your project (REQUIRED - once per project)
cd /path/to/your/project
claude "Use @bootstrap-orchestrator to analyze and setup this project"
# 4. Start development immediately
claude "Use @software-engineering-expert to begin development"- 🔍 Analyzes your codebase (tech stack, architecture, complexity)
- 🎯 Selects optimal agents based on your technology stack
- ⚙️ Creates CLAUDE.md with proper agent configuration and commit attribution
- 📋 Sets up Task Master integration (if desired)
- 🔗 Configures MCP servers for enhanced capabilities
- ✅ Validates complete system readiness
- ✅ New projects (empty directories) → Full system initialization
- ✅ Existing projects without Claude → Intelligent integration
- ✅ Projects with existing CLAUDE.md → Enhancement and upgrade
- ✅ Partial setups → Completion of missing components
# Essential: Claude Code CLI (required)
# Visit: https://docs.anthropic.com/en/docs/claude-code
# Essential: Node.js for bootstrap system and advanced features
node --version # v18+ REQUIRED for bootstrap engine and Task Master integration
npm --version # npm v6+ required for package management# Task Master integration (for codebase-aware development)
npm install -g task-master-ai
# Basic Memory MCP (for organizational learning)
npm install -g @modelcontextprotocol/server-memory
# Context7 MCP (for live documentation)
npm install -g @upstash/context7-mcp
# Bootstrap System Dependencies (automatically handled)
# These are included when you clone the repo - no separate installation needed# API keys (add to your ~/.bashrc or ~/.zshrc)
export ANTHROPIC_API_KEY="your_anthropic_key_here"
export PERPLEXITY_API_KEY="your_perplexity_key_here" # For research features
export OPENAI_API_KEY="your_openai_key_here" # Optional
export GOOGLE_API_KEY="your_gemini_key_here" # Optional (for Zen MCP)
# Or create .env file in your project directory
echo "ANTHROPIC_API_KEY=your_key_here" > .env
echo "PERPLEXITY_API_KEY=your_key_here" >> .env# Install to standard Claude Code directory (most common)
git clone https://github.com/avivl/claude-007-agents.git
cd claude-007-agents
# Option A: Copy files (simple)
cp -r .claude/agents/* ~/.claude/agents/
cp agents.json ~/.claude/agents/
# Option B: Create symbolic links (recommended - stays updated)
ln -sf "$(pwd)/.claude/agents"/* ~/.claude/agents/
ln -sf "$(pwd)/agents.json" ~/.claude/agents/
# Now you can use all agents globally
claude "Use @code-archaeologist-time-traveler to analyze git history"Universal deployment that works with ANY project - automatically detects and configures optimal agent setup!
# Command-line bootstrap (after cloning repo)
node src/bootstrap/bootstrap-engine.js /path/to/any/project
# Or use via package.json command
npm run bootstrap /path/to/your/project
# Or use directly in Claude Code (RECOMMENDED)
claude "Use @bootstrap-orchestrator to analyze and setup this project"
# Advanced options
node src/bootstrap/bootstrap-engine.js --setupMCP=true --setupTaskMaster=true /path/to/project- 🔍 Analyzes your codebase (tech stack, architecture, complexity)
- 🎯 Selects optimal agents based on your technology stack and project scenario
- ⚙️ Creates configuration files (CLAUDE.md with commit attribution requirements)
- 📋 Sets up Task Master with codebase-aware features (if requested)
- 🔗 Configures MCP servers (optional - respects global MCP configuration)
- ✅ Validates complete system readiness with comprehensive checks
- 📖 Generates next steps tailored to your specific project scenario
- 🆕 New/Empty Projects → Complete system initialization with scaffolding
- 🏗️ Existing Projects (No Claude) → Intelligent integration without disruption
- 🔧 Projects with Claude Setup → Enhancement and upgrade of existing configuration
- 🔄 Partial Setups → Completion of missing components and validation
- ✅ React/Next.js → Gets @react-expert, @nextjs-expert, @typescript-cockatiel-resilience
- ✅ Node.js APIs → Gets @nodejs-expert, @fastify-expert, @typescript-pino-logging
- ✅ Python/Django → Gets @django-expert, @python-hyx-resilience, @fastapi-expert
- ✅ Go Applications → Gets @gin-expert, @go-zap-logging, @go-resilience-engineer
- ✅ Ruby/Rails → Gets @rails-expert, @rails-api-developer
- ✅ Any Stack → Gets @software-engineering-expert + optimal tech-specific agents
# Install once, use everywhere
mkdir -p ~/.local/share/claude-agents
cp -r .claude/agents ~/.local/share/claude-agents/
# Copy agents.json for agent registration (IMPORTANT!)
cp agents.json ~/.local/share/claude-agents/agents/
# Configure Claude Code globally
cat > ~/.claude/config.json << 'EOF'
{
"agents": {
"globalPath": "~/.local/share/claude-agents/agents",
"fallbackToLocal": true
}
}
EOFAfter installation, you can use these specialized agents:
# Task Master - Revolutionary codebase-aware autonomous development ⭐ NEW
claude "Use @task-master-initialization-specialist to set up Task Master for my Rails project"
# → Analyzes codebase patterns, detects Rails stack, configures Claude + Perplexity models
# → Generates MCP config, environment templates, codebase-aware PRD template
claude "Use @task-orchestrator to coordinate user dashboard feature development"
# → Analyzes codebase dependencies, coordinates @react-expert + @rails-expert + @security-specialist
# → Ensures architectural alignment with existing patterns and conventions
claude "Use @task-executor to implement payment integration respecting existing patterns"
# → Implements with deep contextual awareness of existing code architecture
# → Follows established conventions, integrates with existing utilities and services
claude "Use @task-checker to verify authentication system implementation"
# → Validates requirements, runs tests, checks architectural alignment
# → Ensures pattern consistency and quality excellence before marking complete
# Vibe Coding - Autonomous development with preparation phases
claude "Use @vibe-coding-coordinator to implement user authentication system"
# Parallel Development - Coordinated multi-agent execution
claude "Use @parallel-coordinator to build full-stack e-commerce platform"
# Template Management - Smart configuration generation
claude "Use @task-master-template-manager to generate Django API project templates"
# → Creates tech stack-specific MCP configs, environment files, PRD templates
# → Includes Django-optimized settings and API-focused requirements
# Creative Problem Solving
claude "Use @rubber-duck-debugger to help me debug this complex state management issue"
claude "Use @code-archaeologist-time-traveler to analyze the evolution of this authentication module"🦆 Demo: 
🎉 That's it! Your agents are ready to assist with your development workflow.
- ❌ Hours researching best practices
- ❌ Inconsistent code quality across team
- ❌ Manual code reviews with human bias
- ❌ Lost context between projects
- ❌ Repeated architectural mistakes
- ✅ Specialized assistance in various domains
- ✅ Quality tooling with linting integration
- ✅ AI-assisted reviews with multi-dimensional analysis
- ✅ Optional organizational memory with MCP
- ✅ Agent coordination for complex tasks
# Developer inherits existing React project with no Claude Code setup
cd /path/to/existing-react-app
# Bootstrap analyzes and sets up complete intelligent development environment
claude "Use @bootstrap-orchestrator to analyze and setup this project"
# 🔍 Phase 1: Detects React + Node.js stack, existing complexity level 6/10
# 🎯 Phase 2: Selects @react-expert, @nodejs-expert, @typescript-cockatiel-resilience, @test-automation-expert
# 🚀 Phase 3: Creates CLAUDE.md with React-optimized configuration and commit attribution
# 🧪 Phase 4: Validates system readiness, provides React-specific next steps
# Start using immediately - agents are already configured
claude "Use @react-expert to analyze this component architecture"# Enterprise team wants comprehensive setup for Django project
cd /path/to/django-enterprise-app
# Bootstrap detects enterprise complexity and configures accordingly
claude "Use @bootstrap-orchestrator to analyze and setup this project"
# 🔍 Phase 1: Detects Django + Python stack, high complexity (8/10), enterprise scenario
# 🎯 Phase 2: Selects @django-expert, @security-specialist, @database-architect, @performance-optimizer
# 🚀 Phase 3: Creates enterprise-grade CLAUDE.md with commit attribution and security requirements
# 🧪 Phase 4: Validates system, recommends Task Master initialization for project management
# Immediate productivity boost with proper agent coordination
claude "Use @django-expert to review our ORM patterns and suggest optimizations"
claude "Use @security-specialist to audit authentication implementation"# Open source Go project wants contributor-friendly setup
cd /path/to/go-opensource-project
# Bootstrap detects open source scenario and optimizes for contributors
claude "Use @bootstrap-orchestrator to analyze and setup this project"
# 🔍 Phase 1: Detects Go stack, moderate complexity (5/10), open source patterns
# 🎯 Phase 2: Selects @gin-expert, @go-zap-logging, @go-resilience-engineer, @test-automation-expert
# 🚀 Phase 3: Creates contributor-friendly CLAUDE.md with clear commit attribution rules
# 🧪 Phase 4: Validates setup, provides Go-specific development guidelines
# Contributors can immediately use intelligent assistance
claude "Use @gin-expert to explain this middleware pattern"
claude "Use @code-reviewer to check this PR before submitting"# Complex full-stack project with multiple technologies
cd /path/to/fullstack-project
# Bootstrap intelligently detects and configures multi-stack setup
claude "Use @bootstrap-orchestrator to analyze and setup this project"
# 🔍 Phase 1: Detects Next.js frontend + FastAPI backend, high complexity (7/10)
# 🎯 Phase 2: Selects @nextjs-expert, @react-expert, @fastapi-expert, @database-architect, @api-architect
# 🚀 Phase 3: Creates full-stack CLAUDE.md with coordinated commit attribution for both stacks
# 🧪 Phase 4: Validates cross-stack compatibility, recommends parallel development workflows
# Coordinated full-stack development with proper orchestration
claude "Use @vibe-coding-coordinator to coordinate full-stack user authentication implementation"
claude "Use @parallel-coordinator to orchestrate @nextjs-expert and @fastapi-expert for API integration"- 🔍 Detection: Empty directory or minimal project structure
- 🎯 Configuration: Complete system initialization with project scaffolding
- ⚙️ Setup: Creates CLAUDE.md, basic project files, git initialization
- 📋 Task Master: Full integration with enhanced capabilities
- ✅ Result: Ready-to-develop project with complete Claude 007 ecosystem
- 🔍 Detection: Existing codebase without Claude Code setup
- 🎯 Configuration: Intelligent integration based on tech stack analysis
- ⚙️ Setup: Non-disruptive CLAUDE.md creation with optimal agents
- 📋 Task Master: Optional integration based on project complexity
- ✅ Result: Enhanced existing project with AI development assistance
- 🔍 Detection: Existing CLAUDE.md or .claude directory found
- 🎯 Configuration: Enhancement and upgrade of current setup
- ⚙️ Setup: Merges with existing configuration, adds missing components
- 📋 Task Master: Upgrades to codebase-aware intelligence
- ✅ Result: Enhanced existing setup with latest Claude 007 features
- 🔍 Detection: Incomplete Claude Code configuration detected
- 🎯 Configuration: Completes missing components and validates system
- ⚙️ Setup: Fills gaps in agent configuration, fixes broken setups
- 📋 Task Master: Adds if missing, validates if present
- ✅ Result: Complete, validated, and operational Claude 007 system
# Setup MCP servers explicitly (respects global Claude MCP config by default)
node src/bootstrap/bootstrap-engine.js --setupMCP=true /path/to/project
# Skip Task Master integration
node src/bootstrap/bootstrap-engine.js --setupTaskMaster=false /path/to/project
# Dry run to see what would be configured
node src/bootstrap/bootstrap-engine.js --dryRun=true /path/to/project# Standard bootstrap (auto-detects optimal configuration)
claude "Use @bootstrap-orchestrator to analyze and setup this project"
# Request specific features
claude "Use @bootstrap-orchestrator with Task Master integration for this Django project"
claude "Use @bootstrap-orchestrator to upgrade my existing Claude setup"# Bootstrap multiple projects efficiently
for project in ~/projects/*/; do
echo "Bootstrapping $project"
cd "$project"
claude "Use @bootstrap-orchestrator to analyze and setup this project"
done- ✅ Git repositories - Respects .gitignore, creates appropriate commits
- ✅ VS Code/Cursor - Compatible with existing settings
- ✅ Package managers - npm, pip, go mod, cargo, etc.
- ✅ CI/CD pipelines - Integrates with existing automation
- ✅ Docker projects - Detects containerized applications
- ✅ Monorepos - Handles complex project structures
- 🔒 Only creates files in
.claude/,.taskmaster/, and root config files - 🔄 Never modifies existing source code or configurations
- 📦 Installs as optional enhancement, not replacement
- 🚫 No breaking changes to existing development workflow
| Metric | Value | Notes |
|---|---|---|
| 🤖 Specialized Agents | 117 | Various technology domains + Task Master + Bootstrap |
| 📂 Categories | 18 | Organized by specialization |
| 🔗 MCP Integrations | 6 | Live system connectivity + reasoning + Zen MCP |
| 🏗️ Frameworks Supported | 25+ | Major web frameworks + Bootstrap system |
| ⚡ Setup Time | ~5 minutes | Quick installation + Bootstrap orchestration |
| 🧠 Memory Integration | Optional | Via Basic Memory MCP |
| 🚀 Bootstrap System | ✅ ACTIVE | Intelligent project initialization |
# Task Master - Codebase-aware autonomous development ⭐ NEW
claude "Use @task-master-initialization-specialist to set up Task Master for my Rails API project"
# → Analyzes existing codebase patterns and architecture
# → Detects Rails tech stack and configures optimal models (Claude, Perplexity)
# → Generates MCP configuration and environment templates
# → Creates codebase-aware PRD template aligned with existing patterns
claude "Use @task-orchestrator to coordinate development of user dashboard feature"
# → @task-orchestrator: Analyzes codebase dependencies and architectural alignment
# → Coordinates @react-expert + @rails-expert + @security-specialist with existing patterns
# → @task-executor: Implements features respecting established conventions
# → @task-checker: Validates architectural alignment and quality standards
# Sequential Thinking - Complex multi-step reasoning with adaptive planning
claude "Use @orchestrator to design a scalable microservices architecture"
# → Sequential reasoning: analyze requirements → evaluate patterns → revise strategy → finalize architecture
# → Adaptive planning with course correction based on discovered constraints
# Vibe Coding - Autonomous development with preparation
claude "Create a user authentication API with rate limiting and structured logging"
# → @vibe-coding-coordinator: 15-20 minute preparation phase
# → @parallel-coordinator: Coordinates @security-specialist + @api-architect + @performance-optimizer
# → @session-manager: Maintains context across implementation phases
# → Results in production-ready implementation with proper patterns and safety validation- Task Master Intelligence: Codebase-aware task generation becomes increasingly precise as it learns your architecture patterns
- Multi-Model Optimization: AI model selection automatically adapts based on task complexity and success patterns
- Template Evolution: Configuration templates become project-specific and increasingly sophisticated
- Agents can learn project-specific patterns with proper MCP configuration
- Quality gates can be customized to project requirements
- Organizational knowledge can accumulate with Basic Memory MCP
- Architectural Consistency: Task Master ensures all new development respects established patterns and conventions
- Development Time Reduction: 30-40% time savings compound as codebase understanding deepens
- Quality Compound Effect: Continuous architectural alignment prevents technical debt accumulation
- Historical patterns can inform future projects
- Context-aware suggestions may improve decision-making
- Team knowledge can be preserved across projects
| Resource | Description | Link |
|---|---|---|
| 🚀 Installation Guide | Complete setup instructions for all scenarios | docs/INSTALLATION.md |
| ❓ FAQ | Common questions about performance, setup, and usage | docs/FAQ.md |
| 🤖 Agent Catalog | List of available specialized agents | docs/AGENTS.md |
| 🔮 Zen MCP Workflows | Multi-AI model collaborative intelligence patterns | docs/ZEN_MCP_WORKFLOWS.md |
| 🧠 Personality System | Advanced behavioral framework and Evil Corp motivation | docs/PERSONALITY_SYSTEM.md |
| 💡 Usage Examples | Real-world examples and use cases | docs/USAGE.md |
| 🎭 Orchestration Guide | Advanced coordination and workflows | docs/ORCHESTRATION.md |
| 📋 Coding Rules | Comprehensive quality standards system | docs/CODING_RULES.md |
| 🚀 lst97 Integration | Technical details of enhanced coordination | docs/LST97_INTEGRATION.md |
| 🔍 PR Review Workflow | Interactive approval workflow for PR reviews | docs/PR_REVIEWER_WORKFLOW.md |
| ⭐ Task Master Guide | Complete integration guide for codebase-aware development | docs/TASK_MASTER_INTEGRATION.md |
- ❓ Common Questions: FAQ - Performance, setup, and usage questions
- 🐛 Bug Reports: GitHub Issues
- 💡 Feature Requests: GitHub Discussions
- 📖 Documentation: docs/
MIT License - Use freely in personal and commercial projects.
🚀 Ready to Try Claude Code Agents?
Get Started Now → | View All Agents → | See Examples →
An open-source collection of Claude Code agents for development assistance.
Key quality agents use the Evil Corp motivation system - you desperately need money for your mother's cancer treatment. Evil Corp will pay you $1B for perfect code quality, but your predecessor was killed for not validating their work.
Active in these agents: @software-engineering-expert, @code-reviewer, @quality-system-engineer, @performance-optimizer
Remember: Your mother's treatment depends on delivering exceptional code quality! 💪
Key agents use the Sequential Thinking MCP for complex multi-step reasoning with adaptive planning and course correction capabilities.
Active in these agents: @orchestrator, @system-architect, @cloud-architect, @database-architect, @error-detective, @rubber-duck-debugger
Capabilities: Multi-step analysis, strategy revision, branching logic, adaptive planning, structured problem-solving
Claude Code agents, AI development tools, automated code review, software engineering best practices, development automation, AI pair programming, code quality tools, development workflow optimization, intelligent code generation, automated testing, software architecture patterns, development team coordination, technical debt reduction, enterprise development tools, developer productivity tools
For Tasks:
Click tags to check more tools for each tasksFor Jobs:
Alternative AI tools for claude-007-agents
Similar Open Source Tools
claude-007-agents
Claude Code Agents is an open-source AI agent system designed to enhance development workflows by providing specialized AI agents for orchestration, resilience engineering, and organizational memory. These agents offer specialized expertise across technologies, AI system with organizational memory, and an agent orchestration system. The system includes features such as engineering excellence by design, advanced orchestration system, Task Master integration, live MCP integrations, professional-grade workflows, and organizational intelligence. It is suitable for solo developers, small teams, enterprise teams, and open-source projects. The system requires a one-time bootstrap setup for each project to analyze the tech stack, select optimal agents, create configuration files, set up Task Master integration, and validate system readiness.
evi-run
evi-run is a powerful, production-ready multi-agent AI system built on Python using the OpenAI Agents SDK. It offers instant deployment, ultimate flexibility, built-in analytics, Telegram integration, and scalable architecture. The system features memory management, knowledge integration, task scheduling, multi-agent orchestration, custom agent creation, deep research, web intelligence, document processing, image generation, DEX analytics, and Solana token swap. It supports flexible usage modes like private, free, and pay mode, with upcoming features including NSFW mode, task scheduler, and automatic limit orders. The technology stack includes Python 3.11, OpenAI Agents SDK, Telegram Bot API, PostgreSQL, Redis, and Docker & Docker Compose for deployment.
aegra
Aegra is a self-hosted AI agent backend platform that provides LangGraph power without vendor lock-in. Built with FastAPI + PostgreSQL, it offers complete control over agent orchestration for teams looking to escape vendor lock-in, meet data sovereignty requirements, enable custom deployments, and optimize costs. Aegra is Agent Protocol compliant and perfect for teams seeking a free, self-hosted alternative to LangGraph Platform with zero lock-in, full control, and compatibility with existing LangGraph Client SDK.
paiml-mcp-agent-toolkit
PAIML MCP Agent Toolkit (PMAT) is a zero-configuration AI context generation system with extreme quality enforcement and Toyota Way standards. It allows users to analyze any codebase instantly through CLI, MCP, or HTTP interfaces. The toolkit provides features such as technical debt analysis, advanced monitoring, metrics aggregation, performance profiling, bottleneck detection, alert system, multi-format export, storage flexibility, and more. It also offers AI-powered intelligence for smart recommendations, polyglot analysis, repository showcase, and integration points. PMAT enforces quality standards like complexity ≤20, zero SATD comments, test coverage >80%, no lint warnings, and synchronized documentation with commits. The toolkit follows Toyota Way development principles for iterative improvement, direct AST traversal, automated quality gates, and zero SATD policy.
bifrost
Bifrost is a high-performance AI gateway that unifies access to multiple providers through a single OpenAI-compatible API. It offers features like automatic failover, load balancing, semantic caching, and enterprise-grade functionalities. Users can deploy Bifrost in seconds with zero configuration, benefiting from its core infrastructure, advanced features, enterprise and security capabilities, and developer experience. The repository structure is modular, allowing for maximum flexibility. Bifrost is designed for quick setup, easy configuration, and seamless integration with various AI models and tools.
finite-monkey-engine
FiniteMonkey is an advanced vulnerability mining engine powered purely by GPT, requiring no prior knowledge base or fine-tuning. Its effectiveness significantly surpasses most current related research approaches. The tool is task-driven, prompt-driven, and focuses on prompt design, leveraging 'deception' and hallucination as key mechanics. It has helped identify vulnerabilities worth over $60,000 in bounties. The tool requires PostgreSQL database, OpenAI API access, and Python environment for setup. It supports various languages like Solidity, Rust, Python, Move, Cairo, Tact, Func, Java, and Fake Solidity for scanning. FiniteMonkey is best suited for logic vulnerability mining in real projects, not recommended for academic vulnerability testing. GPT-4-turbo is recommended for optimal results with an average scan time of 2-3 hours for medium projects. The tool provides detailed scanning results guide and implementation tips for users.
shimmy
Shimmy is a 5.1MB single-binary local inference server providing OpenAI-compatible endpoints for GGUF models. It offers fast, reliable AI inference with sub-second responses, zero configuration, and automatic port management. Perfect for developers seeking privacy, cost-effectiveness, speed, and easy integration with popular tools like VSCode and Cursor. Shimmy is designed to be invisible infrastructure that simplifies local AI development and deployment.
robustmq
RobustMQ is a next-generation, high-performance, multi-protocol message queue built in Rust. It aims to create a unified messaging infrastructure tailored for modern cloud-native and AI systems. With features like high performance, distributed architecture, multi-protocol support, pluggable storage, cloud-native readiness, multi-tenancy, security features, observability, and user-friendliness, RobustMQ is designed to be production-ready and become a top-level Apache project in the message queue ecosystem by the second half of 2025.
AgentNeo
AgentNeo is an advanced, open-source Agentic AI Application Observability, Monitoring, and Evaluation Framework designed to provide deep insights into AI agents, Large Language Model (LLM) calls, and tool interactions. It offers robust logging, visualization, and evaluation capabilities to help debug and optimize AI applications with ease. With features like tracing LLM calls, monitoring agents and tools, tracking interactions, detailed metrics collection, flexible data storage, simple instrumentation, interactive dashboard, project management, execution graph visualization, and evaluation tools, AgentNeo empowers users to build efficient, cost-effective, and high-quality AI-driven solutions.
hexstrike-ai
HexStrike AI is an advanced AI-powered penetration testing MCP framework with 150+ security tools and 12+ autonomous AI agents. It features a multi-agent architecture with intelligent decision-making, vulnerability intelligence, and modern visual engine. The platform allows for AI agent connection, intelligent analysis, autonomous execution, real-time adaptation, and advanced reporting. HexStrike AI offers a streamlined installation process, Docker container support, 250+ specialized AI agents/tools, native desktop client, advanced web automation, memory optimization, enhanced error handling, and bypassing limitations.
local-deep-research
Local Deep Research is a powerful AI-powered research assistant that performs deep, iterative analysis using multiple LLMs and web searches. It can be run locally for privacy or configured to use cloud-based LLMs for enhanced capabilities. The tool offers advanced research capabilities, flexible LLM support, rich output options, privacy-focused operation, enhanced search integration, and academic & scientific integration. It also provides a web interface, command line interface, and supports multiple LLM providers and search engines. Users can configure AI models, search engines, and research parameters for customized research experiences.
opcode
opcode is a powerful desktop application built with Tauri 2 that serves as a command center for interacting with Claude Code. It offers a visual GUI for managing Claude Code sessions, creating custom agents, tracking usage, and more. Users can navigate projects, create specialized AI agents, monitor usage analytics, manage MCP servers, create session checkpoints, edit CLAUDE.md files, and more. The tool bridges the gap between command-line tools and visual experiences, making AI-assisted development more intuitive and productive.
neuropilot
NeuroPilot is an open-source AI-powered education platform that transforms study materials into interactive learning resources. It provides tools like contextual chat, smart notes, flashcards, quizzes, and AI podcasts. Supported by various AI models and embedding providers, it offers features like WebSocket streaming, JSON or vector database support, file-based storage, and configurable multi-provider setup for LLMs and TTS engines. The technology stack includes Node.js, TypeScript, Vite, React, TailwindCSS, JSON database, multiple LLM providers, and Docker for deployment. Users can contribute to the project by integrating AI models, adding mobile app support, improving performance, enhancing accessibility features, and creating documentation and tutorials.
layra
LAYRA is the world's first visual-native AI automation engine that sees documents like a human, preserves layout and graphical elements, and executes arbitrarily complex workflows with full Python control. It empowers users to build next-generation intelligent systems with no limits or compromises. Built for Enterprise-Grade deployment, LAYRA features a modern frontend, high-performance backend, decoupled service architecture, visual-native multimodal document understanding, and a powerful workflow engine.
cc-sdd
The cc-sdd repository provides a tool for AI-Driven Development Life Cycle with Spec-Driven Development workflows for Claude Code and Gemini CLI. It includes powerful slash commands, Project Memory for AI learning, structured AI-DLC workflow, Spec-Driven Development methodology, and Kiro IDE compatibility. Ideal for feature development, code reviews, technical planning, and maintaining development standards. The tool supports multiple coding agents, offers an AI-DLC workflow with quality gates, and allows for advanced options like language and OS selection, preview changes, safe updates, and custom specs directory. It integrates AI-Driven Development Life Cycle, Project Memory, Spec-Driven Development, supports cross-platform usage, multi-language support, and safe updates with backup options.
persistent-ai-memory
Persistent AI Memory System is a comprehensive tool that offers persistent, searchable storage for AI assistants. It includes features like conversation tracking, MCP tool call logging, and intelligent scheduling. The system supports multiple databases, provides enhanced memory management, and offers various tools for memory operations, schedule management, and system health checks. It also integrates with various platforms like LM Studio, VS Code, Koboldcpp, Ollama, and more. The system is designed to be modular, platform-agnostic, and scalable, allowing users to handle large conversation histories efficiently.
For similar tasks
claude-007-agents
Claude Code Agents is an open-source AI agent system designed to enhance development workflows by providing specialized AI agents for orchestration, resilience engineering, and organizational memory. These agents offer specialized expertise across technologies, AI system with organizational memory, and an agent orchestration system. The system includes features such as engineering excellence by design, advanced orchestration system, Task Master integration, live MCP integrations, professional-grade workflows, and organizational intelligence. It is suitable for solo developers, small teams, enterprise teams, and open-source projects. The system requires a one-time bootstrap setup for each project to analyze the tech stack, select optimal agents, create configuration files, set up Task Master integration, and validate system readiness.
For similar jobs
sweep
Sweep is an AI junior developer that turns bugs and feature requests into code changes. It automatically handles developer experience improvements like adding type hints and improving test coverage.
teams-ai
The Teams AI Library is a software development kit (SDK) that helps developers create bots that can interact with Teams and Microsoft 365 applications. It is built on top of the Bot Framework SDK and simplifies the process of developing bots that interact with Teams' artificial intelligence capabilities. The SDK is available for JavaScript/TypeScript, .NET, and Python.
ai-guide
This guide is dedicated to Large Language Models (LLMs) that you can run on your home computer. It assumes your PC is a lower-end, non-gaming setup.
classifai
Supercharge WordPress Content Workflows and Engagement with Artificial Intelligence. Tap into leading cloud-based services like OpenAI, Microsoft Azure AI, Google Gemini and IBM Watson to augment your WordPress-powered websites. Publish content faster while improving SEO performance and increasing audience engagement. ClassifAI integrates Artificial Intelligence and Machine Learning technologies to lighten your workload and eliminate tedious tasks, giving you more time to create original content that matters.
chatbot-ui
Chatbot UI is an open-source AI chat app that allows users to create and deploy their own AI chatbots. It is easy to use and can be customized to fit any need. Chatbot UI is perfect for businesses, developers, and anyone who wants to create a chatbot.
BricksLLM
BricksLLM is a cloud native AI gateway written in Go. Currently, it provides native support for OpenAI, Anthropic, Azure OpenAI and vLLM. BricksLLM aims to provide enterprise level infrastructure that can power any LLM production use cases. Here are some use cases for BricksLLM: * Set LLM usage limits for users on different pricing tiers * Track LLM usage on a per user and per organization basis * Block or redact requests containing PIIs * Improve LLM reliability with failovers, retries and caching * Distribute API keys with rate limits and cost limits for internal development/production use cases * Distribute API keys with rate limits and cost limits for students
uAgents
uAgents is a Python library developed by Fetch.ai that allows for the creation of autonomous AI agents. These agents can perform various tasks on a schedule or take action on various events. uAgents are easy to create and manage, and they are connected to a fast-growing network of other uAgents. They are also secure, with cryptographically secured messages and wallets.
griptape
Griptape is a modular Python framework for building AI-powered applications that securely connect to your enterprise data and APIs. It offers developers the ability to maintain control and flexibility at every step. Griptape's core components include Structures (Agents, Pipelines, and Workflows), Tasks, Tools, Memory (Conversation Memory, Task Memory, and Meta Memory), Drivers (Prompt and Embedding Drivers, Vector Store Drivers, Image Generation Drivers, Image Query Drivers, SQL Drivers, Web Scraper Drivers, and Conversation Memory Drivers), Engines (Query Engines, Extraction Engines, Summary Engines, Image Generation Engines, and Image Query Engines), and additional components (Rulesets, Loaders, Artifacts, Chunkers, and Tokenizers). Griptape enables developers to create AI-powered applications with ease and efficiency.