vibeship-spark-intelligence

Spark Intelligence is a self-evolving AI companion that runs 100% on your machine as a local AI companion. It captures, distills, transforms, and delivers advisory context to help you act with better context. It is designed to convert experience into adaptive operational behavior, not just stored memory. The tool is beyond a learning loop, continuously learning and growing smarter through use. It provides a distillation pipeline, transformation layer, advisory delivery, EIDOS loop, domain chips, observability surfaces, and a CLI for easy interaction. The architecture involves event capture, queue, bridge worker, pipeline, quality gate, cognitive learner, and more. The Obsidian Observatory integration allows users to browse, search, and query insights, decisions, and quality verdicts in a human-readable vault.

iloom is a tool designed to streamline AI-assisted development by focusing on maintaining alignment between human developers and AI agents. It treats context as a first-class concern, persisting AI reasoning in issue comments rather than temporary chats. The tool allows users to collaborate with AI agents in an isolated environment, switch between complex features without losing context, document AI decisions publicly, and capture key insights and lessons learned from AI sessions. iloom is not just a tool for managing git worktrees, but a control plane for maintaining alignment between users and their AI assistants.

PostgresAI is an AI-native PostgreSQL observability tool designed for monitoring, health checks, and root cause analysis. It provides structured reports and metrics for AI consumption, tracks problems from detection to resolution, offers over 45 health checks including bloat, indexes, queries, settings, and security, and features Active Session History similar to Oracle ASH. PostgresAI is part of the Self-Driving Postgres initiative, aiming to make Postgres autonomous. It includes expert dashboards following the Four Golden Signals methodology and is battle-tested with companies like GitLab, Miro, Chewy, and more.

Empirica is an epistemic self-awareness framework for AI agents to understand their knowledge boundaries. It introduces epistemic vectors to measure knowledge state and uncertainty, enabling honest communication. The tool emerged from 600+ real working sessions across various AI systems, providing cognitive infrastructure for distinguishing between confident knowledge and guessing. Empirica's 13 foundational vectors cover engagement, domain knowledge depth, execution capability, information access, understanding clarity, coherence, signal-to-noise ratio, information richness, working state, progress rate, task completion level, work significance, and explicit doubt tracking. It is applicable across industries like software development, research, healthcare, legal, education, and finance, aiding in tasks such as code review, hypothesis testing, diagnostic confidence, case analysis, learning assessment, and risk assessment.

Evalchemy is a unified and easy-to-use toolkit for evaluating language models, focusing on post-trained models. It integrates multiple existing benchmarks such as RepoBench, AlpacaEval, and ZeroEval. Key features include unified installation, parallel evaluation, simplified usage, and results management. Users can run various benchmarks with a consistent command-line interface and track results locally or integrate with a database for systematic tracking and leaderboard submission.

AI Runner is a multi-modal AI interface that allows users to run open-source large language models and AI image generators on their own hardware. The tool provides features such as voice-based chatbot conversations, text-to-speech, speech-to-text, vision-to-text, text generation with large language models, image generation capabilities, image manipulation tools, utility functions, and more. It aims to provide a stable and user-friendly experience with security updates, a new UI, and a streamlined installation process. The application is designed to run offline on users' hardware without relying on a web server, offering a smooth and responsive user experience.

LEANN is an innovative vector database that democratizes personal AI, transforming your laptop into a powerful RAG system that can index and search through millions of documents using 97% less storage than traditional solutions without accuracy loss. It achieves this through graph-based selective recomputation and high-degree preserving pruning, computing embeddings on-demand instead of storing them all. LEANN allows semantic search of file system, emails, browser history, chat history, codebase, or external knowledge bases on your laptop with zero cloud costs and complete privacy. It is a drop-in semantic search MCP service fully compatible with Claude Code, enabling intelligent retrieval without changing your workflow.

Optopsy is a fast, flexible backtesting library for options strategies in Python. It helps users generate comprehensive performance statistics from historical options data to answer questions like 'How do iron condors perform on SPX?' or 'What delta range produces the best results for covered calls?' The library features an AI Chat UI for natural language interaction, a trade simulator for full trade-by-trade simulation, 28 built-in strategies, live data providers, smart caching, entry signals with TA indicators, and returns DataFrames that integrate with existing workflows.

Explain OpenClaw is a comprehensive documentation repository for the OpenClaw framework, a self-hosted AI assistant platform. It covers various aspects such as plain English explanations, technical architecture, deployment scenarios, privacy and safety measures, security audits, worst-case security scenarios, optimizations, and AI model comparisons. The repository serves as a living knowledge base with beginner-friendly explanations and detailed technical insights for contributors.

Parlant is a structured approach to building and guiding customer-facing AI agents. It allows developers to create and manage robust AI agents, providing specific feedback on agent behavior and helping understand user intentions better. With features like guidelines, glossary, coherence checks, dynamic context, and guided tool use, Parlant offers control over agent responses and behavior. Developer-friendly aspects include instant changes, Git integration, clean architecture, and type safety. It enables confident deployment with scalability, effective debugging, and validation before deployment. Parlant works with major LLM providers and offers client SDKs for Python and TypeScript. The tool facilitates natural customer interactions through asynchronous communication and provides a chat UI for testing new behaviors before deployment.

Squad is an AI development tool that provides a team of specialists (frontend, backend, tester, lead) through GitHub Copilot. Each team member runs in its own context, learns your codebase, shares decisions, and improves over time. The tool works by launching agents in parallel to work on tasks simultaneously, with knowledge compounding across sessions. Squad stores team-wide decisions in `decisions.md` and individual agent learnings in `history.md`. The tool operates within a 200K token context window per agent, with optimizations to maximize actual work capacity. Squad's memory architecture includes `charter.md`, `history.md`, `decisions.md`, and `log/` for session history. The tool creates a `.ai-team/` folder with team roster, routing, decisions, and agent information, ensuring persistence and knowledge sharing. Squad allows for adding and removing team members, review protocols, and issue assignment and triage integration with GitHub Issues. It offers various features like client compatibility, VS Code support, project boards integration, label taxonomy, notifications, MCP setup guide, plugin marketplace, universe expansion, and more.

Factorio Learning Environment is an open source framework designed for developing and evaluating LLM agents in the game of Factorio. It provides two settings: Lab-play with structured tasks and Open-play for building large factories. Results show limitations in spatial reasoning and automation strategies. Agents interact with the environment through code synthesis, observation, action, and feedback. Tools are provided for game actions and state representation. Agents operate in episodes with observation, planning, and action execution. Tasks specify agent goals and are implemented in JSON files. The project structure includes directories for agents, environment, cluster, data, docs, eval, and more. A database is used for checkpointing agent steps. Benchmarks show performance metrics for different configurations.

Metis is an open-source, AI-driven tool for deep security code review, created by Arm's Product Security Team. It helps engineers detect subtle vulnerabilities, improve secure coding practices, and reduce review fatigue. Metis uses LLMs for semantic understanding and reasoning, RAG for context-aware reviews, and supports multiple languages and vector store backends. It provides a plugin-friendly and extensible architecture, named after the Greek goddess of wisdom, Metis. The tool is designed for large, complex, or legacy codebases where traditional tooling falls short.

uLoopMCP is a Unity integration tool designed to let AI drive your Unity project forward with minimal human intervention. It provides a 'self-hosted development loop' where an AI can compile, run tests, inspect logs, and fix issues using tools like compile, run-tests, get-logs, and clear-console. It also allows AI to operate the Unity Editor itself—creating objects, calling menu items, inspecting scenes, and refining UI layouts from screenshots via tools like execute-dynamic-code, execute-menu-item, and capture-window. The tool enables AI-driven development loops to run autonomously inside existing Unity projects.

Open Mercato is a modern, AI-supportive platform designed for shipping enterprise-grade CRMs, ERPs, and commerce backends. It offers modular architecture, custom entities, multi-tenancy, RBAC, data indexing, event workflows, and more. The tool is built with a modern stack including Next.js, TypeScript, zod, Awilix DI, MikroORM, and bcryptjs. It also features an AI Assistant for schema discovery, API execution, and hybrid search. Open Mercato provides data encryption, migration guides, Docker setups, standalone app creation, and follows a spec-driven development approach. The Enterprise Edition offers additional support, SLA options, and advanced features beyond the open-source Core version.

LLMLight is a novel framework that employs Large Language Models (LLMs) as decision-making agents for Traffic Signal Control (TSC). The framework leverages the advanced generalization capabilities of LLMs to engage in a reasoning and decision-making process akin to human intuition for effective traffic control. LLMLight has been demonstrated to be remarkably effective, generalizable, and interpretable against various transportation-based and RL-based baselines on nine real-world and synthetic datasets.

Spark Intelligence is a self-evolving AI companion that runs 100% on your machine as a local AI companion. It captures, distills, transforms, and delivers advisory context to help you act with better context. It is designed to convert experience into adaptive operational behavior, not just stored memory. The tool is beyond a learning loop, continuously learning and growing smarter through use. It provides a distillation pipeline, transformation layer, advisory delivery, EIDOS loop, domain chips, observability surfaces, and a CLI for easy interaction. The architecture involves event capture, queue, bridge worker, pipeline, quality gate, cognitive learner, and more. The Obsidian Observatory integration allows users to browse, search, and query insights, decisions, and quality verdicts in a human-readable vault.

Weave is a toolkit for developing Generative AI applications, built by Weights & Biases. With Weave, you can log and debug language model inputs, outputs, and traces; build rigorous, apples-to-apples evaluations for language model use cases; and organize all the information generated across the LLM workflow, from experimentation to evaluations to production. Weave aims to bring rigor, best-practices, and composability to the inherently experimental process of developing Generative AI software, without introducing cognitive overhead.

LLMStack is a no-code platform for building generative AI agents, workflows, and chatbots. It allows users to connect their own data, internal tools, and GPT-powered models without any coding experience. LLMStack can be deployed to the cloud or on-premise and can be accessed via HTTP API or triggered from Slack or Discord.

The VisionCraft API is a free API for using over 100 different AI models. From images to sound.

Kaito is an operator that automates the AI/ML inference model deployment in a Kubernetes cluster. It manages large model files using container images, avoids tuning deployment parameters to fit GPU hardware by providing preset configurations, auto-provisions GPU nodes based on model requirements, and hosts large model images in the public Microsoft Container Registry (MCR) if the license allows. Using Kaito, the workflow of onboarding large AI inference models in Kubernetes is largely simplified.

PyRIT is an open access automation framework designed to empower security professionals and ML engineers to red team foundation models and their applications. It automates AI Red Teaming tasks to allow operators to focus on more complicated and time-consuming tasks and can also identify security harms such as misuse (e.g., malware generation, jailbreaking), and privacy harms (e.g., identity theft). The goal is to allow researchers to have a baseline of how well their model and entire inference pipeline is doing against different harm categories and to be able to compare that baseline to future iterations of their model. This allows them to have empirical data on how well their model is doing today, and detect any degradation of performance based on future improvements.

Tabby is a self-hosted AI coding assistant, offering an open-source and on-premises alternative to GitHub Copilot. It boasts several key features: * Self-contained, with no need for a DBMS or cloud service. * OpenAPI interface, easy to integrate with existing infrastructure (e.g Cloud IDE). * Supports consumer-grade GPUs.

SPEAR (Simulator for Photorealistic Embodied AI Research) is a powerful tool for training embodied agents. It features 300 unique virtual indoor environments with 2,566 unique rooms and 17,234 unique objects that can be manipulated individually. Each environment is designed by a professional artist and features detailed geometry, photorealistic materials, and a unique floor plan and object layout. SPEAR is implemented as Unreal Engine assets and provides an OpenAI Gym interface for interacting with the environments via Python.

Magick is a groundbreaking visual AIDE (Artificial Intelligence Development Environment) for no-code data pipelines and multimodal agents. Magick can connect to other services and comes with nodes and templates well-suited for intelligent agents, chatbots, complex reasoning systems and realistic characters.