
solana-agent-kit
connect any ai agents to solana protocols
Stars: 750

Solana Agent Kit is an open-source toolkit designed for connecting AI agents to Solana protocols. It enables agents, regardless of the model used, to autonomously perform various Solana actions such as trading tokens, launching new tokens, lending assets, sending compressed airdrops, executing blinks, and more. The toolkit integrates core blockchain features like token operations, NFT management via Metaplex, DeFi integration, Solana blinks, AI integration features with LangChain, autonomous modes, and AI tools. It provides ready-to-use tools for blockchain operations, supports autonomous agent actions, and offers features like memory management, real-time feedback, and error handling. Solana Agent Kit facilitates tasks such as deploying tokens, creating NFT collections, swapping tokens, lending tokens, staking SOL, and sending SPL token airdrops via ZK compression. It also includes functionalities for fetching price data from Pyth and relies on key Solana and Metaplex libraries for its operations.
README:
An open-source toolkit for connecting AI agents to Solana protocols. Now, any agent, using any model can autonomously perform 15+ Solana actions:
- Trade tokens
- Launch new tokens
- Lend assets
- Send compressed airdrops
- Execute blinks
- Launch tokens on AMMs
- And more...
Anyone - whether an SF-based AI researcher or a crypto-native builder - can bring their AI agents trained with any model and seamlessly integrate with Solana.
Replit template created by Arpit Singh
-
Token Operations
- Deploy SPL tokens by Metaplex
- Transfer assets
- Balance checks
- Stake SOL
- Zk compressed Airdrop by Light Protocol and Helius
-
NFTs on 3.Land
- Create your own collection
- NFT creation and automatic listing on 3.land
- List your NFT for sale in any SPL token
-
NFT Management via Metaplex
- Collection deployment
- NFT minting
- Metadata management
- Royalty configuration
-
DeFi Integration
- Jupiter Exchange swaps
- Launch on Pump via PumpPortal
- Raydium pool creation (CPMM, CLMM, AMMv4)
- Orca Whirlpool integration
- Manifest market creation, and limit orders
- Meteora Dynamic AMM, DLMM Pool, and Alpha Vault
- Openbook market creation
- Register and Resolve SNS
- Jito Bundles
- Pyth Price feeds for fetching Asset Prices
- Register/resolve Alldomains
- Perpetuals Trading with Adrena Protocol
- Drift Vaults, Perps, Lending and Borrowing
-
Solana Blinks
- Lending by Lulo (Best APR for USDC)
- Send Arcade Games
- JupSOL staking
- Solayer SOL (sSOL)staking
-
Non-Financial Actions
- Gib Work for registering bounties
-
LangChain Integration
- Ready-to-use LangChain tools for blockchain operations
- Autonomous agent support with React framework
- Memory management for persistent interactions
- Streaming responses for real-time feedback
-
Vercel AI SDK Integration
- Vercel AI SDK for AI agent integration
- Framework agnostic support
- Quick and easy toolkit setup
-
Autonomous Modes
- Interactive chat mode for guided operations
- Autonomous mode for independent agent actions
- Configurable action intervals
- Built-in error handling and recovery
-
AI Tools
- DALL-E integration for NFT artwork generation
- Natural language processing for blockchain commands
- Price feed integration for market analysis
- Automated decision-making capabilities
You can view the full documentation of the kit at docs.solanaagentkit.xyz
npm install solana-agent-kit
import { SolanaAgentKit, createSolanaTools } from "solana-agent-kit";
// Initialize with private key and optional RPC URL
const agent = new SolanaAgentKit(
"your-wallet-private-key-as-base58",
"https://api.mainnet-beta.solana.com",
"your-openai-api-key"
);
// Create LangChain tools
const tools = createSolanaTools(agent);
const result = await agent.deployToken(
"my ai token", // name
"uri", // uri
"token", // symbol
9, // decimals
1000000 // initial supply
);
console.log("Token Mint Address:", result.mint.toString());
const isDevnet = true; // (Optional) if not present TX takes place in Mainnet
const collectionOpts: CreateCollectionOptions = {
collectionName: "",
collectionSymbol: "",
collectionDescription: "",
mainImageUrl: ""
};
const result = await agent.create3LandCollection(
collectionOpts,
isDevnet, // (Optional) if not present TX takes place in Mainnet
);
When creating an NFT using 3Land's tool, it automatically goes for sale on 3.land website
const isDevnet = true; // (Optional) if not present TX takes place in Mainnet
const withPool = true; // (Optional) only present if NFT will be created with a Liquidity Pool for a specific SPL token
const collectionAccount = ""; //hash for the collection
const createItemOptions: CreateSingleOptions = {
itemName: "",
sellerFee: 500, //5%
itemAmount: 100, //total items to be created
itemSymbol: "",
itemDescription: "",
traits: [
{ trait_type: "", value: "" },
],
price: 0, //100000000 == 0.1 sol, can be set to 0 for a free mint
splHash: "", //present if listing is on a specific SPL token, if not present sale will be on $SOL, must be present if "withPool" is true
poolName: "", // Only present if "withPool" is true
mainImageUrl: "",
};
const result = await agent.create3LandNft(
collectionAccount,
createItemOptions,
isDevnet, // (Optional) if not present TX takes place in Mainnet
withPool
);
const collection = await agent.deployCollection({
name: "My NFT Collection",
uri: "https://arweave.net/metadata.json",
royaltyBasisPoints: 500, // 5%
creators: [
{
address: "creator-wallet-address",
percentage: 100,
},
],
});
import { PublicKey } from "@solana/web3.js";
const signature = await agent.trade(
new PublicKey("target-token-mint"),
100, // amount
new PublicKey("source-token-mint"),
300 // 3% slippage
);
import { PublicKey } from "@solana/web3.js";
const signature = await agent.lendAssets(
100 // amount of USDC to lend
);
const signature = await agent.stake(
1 // amount in SOL to stake
);
const signature = await agent.restake(
1 // amount in SOL to stake
);
import { PublicKey } from "@solana/web3.js";
(async () => {
console.log(
"~Airdrop cost estimate:",
getAirdropCostEstimate(
1000, // recipients
30_000 // priority fee in lamports
)
);
const signature = await agent.sendCompressedAirdrop(
new PublicKey("JUPyiwrYJFskUPiHa7hkeR8VUtAeFoSYbKedZNsDvCN"), // mint
42, // amount per recipient
[
new PublicKey("1nc1nerator11111111111111111111111111111111"),
// ... add more recipients
],
30_000 // priority fee in lamports
);
})();
const priceFeedID = await agent.getPythPriceFeedID("SOL");
const price = await agent.getPythPrice(priceFeedID);
console.log("Price of SOL/USD:", price);
import { PublicKey } from "@solana/web3.js";
const signature = await agent.openPerpTradeLong({
price: 300, // $300 SOL Max price
collateralAmount: 10, // 10 jitoSOL in
collateralMint: new PublicKey("J1toso1uCk3RLmjorhTtrVwY9HJ7X8V9yYac6Y7kGCPn"), // jitoSOL
leverage: 50000, // x5
tradeMint: new PublicKey("J1toso1uCk3RLmjorhTtrVwY9HJ7X8V9yYac6Y7kGCPn"), // jitoSOL
slippage: 0.3, // 0.3%
});
import { PublicKey } from "@solana/web3.js";
const signature = await agent.closePerpTradeLong({
price: 200, // $200 SOL price
tradeMint: new PublicKey("J1toso1uCk3RLmjorhTtrVwY9HJ7X8V9yYac6Y7kGCPn"), // jitoSOL
});
const { signature } = await agent.closeEmptyTokenAccounts();
Create a drift account with an initial token deposit.
const result = await agent.createDriftUserAccount()
Create a drift vault.
const signature = await agent.createDriftVault({
name: "my-drift-vault",
marketName: "USDC-SPOT",
redeemPeriod: 1, // in days
maxTokens: 100000, // in token units e.g 100000 USDC
minDepositAmount: 5, // in token units e.g 5 USDC
managementFee: 1, // 1%
profitShare: 10, // 10%
hurdleRate: 5, // 5%
permissioned: false, // public vault or whitelist
})
Deposit tokens into a drift vault.
const signature = await agent.depositIntoDriftVault(100, "41Y8C4oxk4zgJT1KXyQr35UhZcfsp5mP86Z2G7UUzojU")
Deposit tokens into your drift account.
const {txSig} = await agent.depositToDriftUserAccount(100, "USDC")
Derive a drift vault address.
const vaultPublicKey = await agent.deriveDriftVaultAddress("my-drift-vault")
Check if agent has a drift account.
const {hasAccount, account} = await agent.doesUserHaveDriftAccount()
Get drift account information.
const accountInfo = await agent.driftUserAccountInfo()
Request withdrawal from drift vault.
const signature = await agent.requestWithdrawalFromDriftVault(100, "41Y8C4oxk4zgJT1KXyQr35UhZcfsp5mP86Z2G7UUzojU")
Open a perpertual trade using a drift vault that is delegated to you.
const signature = await agent.tradeUsingDelegatedDriftVault({
vault: "41Y8C4oxk4zgJT1KXyQr35UhZcfsp5mP86Z2G7UUzojU",
amount: 500,
symbol: "SOL",
action: "long",
type: "limit",
price: 180 // Please long limit order at $180/SOL
})
Open a perpertual trade using your drift account.
const signature = await agent.tradeUsingDriftPerpAccount({
amount: 500,
symbol: "SOL",
action: "long",
type: "limit",
price: 180 // Please long limit order at $180/SOL
})
Update drift vault parameters.
const signature = await agent.updateDriftVault({
name: "my-drift-vault",
marketName: "USDC-SPOT",
redeemPeriod: 1, // in days
maxTokens: 100000, // in token units e.g 100000 USDC
minDepositAmount: 5, // in token units e.g 5 USDC
managementFee: 1, // 1%
profitShare: 10, // 10%
hurdleRate: 5, // 5%
permissioned: false, // public vault or whitelist
})
Withdraw tokens from your drift account.
const {txSig} = await agent.withdrawFromDriftAccount(100, "USDC")
Borrow tokens from drift.
const {txSig} = await agent.withdrawFromDriftAccount(1, "SOL", true)
Repay a loan from drift.
const {txSig} = await agent.depositToDriftUserAccount(1, "SOL", true)
Withdraw tokens from a drift vault after the redemption period has elapsed.
const signature = await agent.withdrawFromDriftVault( "41Y8C4oxk4zgJT1KXyQr35UhZcfsp5mP86Z2G7UUzojU")
Update the address a drift vault is delegated to.
const signature = await agent.updateDriftVaultDelegate("41Y8C4oxk4zgJT1KXyQr35UhZcfsp5mP86Z2G7UUzojU", "new-address")
Get the current position values and total value of assets in a Voltr vault.
const values = await agent.voltrGetPositionValues("7opUkqYtxmQRriZvwZkPcg6LqmGjAh1RSEsVrdsGDx5K")
Deposit assets into a specific strategy within a Voltr vault.
const signature = await agent.voltrDepositStrategy(
new BN("1000000000"), // amount in base units (e.g., 1 USDC = 1000000)
"7opUkqYtxmQRriZvwZkPcg6LqmGjAh1RSEsVrdsGDx5K", // vault
"9ZQQYvr4x7AMqd6abVa1f5duGjti5wk1MHsX6hogPsLk" // strategy
)
Withdraw assets from a specific strategy within a Voltr vault.
const signature = await agent.voltrWithdrawStrategy(
new BN("1000000000"), // amount in base units (e.g., 1 USDC = 1000000)
"7opUkqYtxmQRriZvwZkPcg6LqmGjAh1RSEsVrdsGDx5K", // vault
"9ZQQYvr4x7AMqd6abVa1f5duGjti5wk1MHsX6hogPsLk" // strategy
)
const asset = await agent.getAsset("41Y8C4oxk4zgJT1KXyQr35UhZcfsp5mP86Z2G7UUzojU")
The repository includes an advanced example of building a multi-agent system using LangGraph and Solana Agent Kit. Located in examples/agent-kit-langgraph
, this example demonstrates:
- Multi-agent architecture using LangGraph's StateGraph
- Specialized agents for different tasks:
- General purpose agent for basic queries
- Transfer/Swap agent for transaction operations
- Read agent for blockchain data queries
- Manager agent for routing and orchestration
- Fully typed TypeScript implementation
- Environment-based configuration
Check out the LangGraph example for a complete implementation of an advanced Solana agent system.
The toolkit relies on several key Solana and Metaplex libraries:
- @solana/web3.js
- @solana/spl-token
- @metaplex-foundation/digital-asset-standard-api
- @metaplex-foundation/mpl-token-metadata
- @metaplex-foundation/mpl-core
- @metaplex-foundation/umi
- @lightprotocol/compressed-token
- @lightprotocol/stateless.js
Contributions are welcome! Please feel free to submit a Pull Request. Refer to CONTRIBUTING.md for detailed guidelines on how to contribute to this project.
Apache-2 License
If you wanna give back any tokens or donations to the OSS community -- The Public Solana Agent Kit Treasury Address:
Solana Network : EKHTbXpsm6YDgJzMkFxNU1LNXeWcUW7Ezf8mjUNQQ4Pa
This toolkit handles private keys and transactions. Always ensure you're using it in a secure environment and never share your private keys.
For Tasks:
Click tags to check more tools for each tasksFor Jobs:
Alternative AI tools for solana-agent-kit
Similar Open Source Tools

solana-agent-kit
Solana Agent Kit is an open-source toolkit designed for connecting AI agents to Solana protocols. It enables agents, regardless of the model used, to autonomously perform various Solana actions such as trading tokens, launching new tokens, lending assets, sending compressed airdrops, executing blinks, and more. The toolkit integrates core blockchain features like token operations, NFT management via Metaplex, DeFi integration, Solana blinks, AI integration features with LangChain, autonomous modes, and AI tools. It provides ready-to-use tools for blockchain operations, supports autonomous agent actions, and offers features like memory management, real-time feedback, and error handling. Solana Agent Kit facilitates tasks such as deploying tokens, creating NFT collections, swapping tokens, lending tokens, staking SOL, and sending SPL token airdrops via ZK compression. It also includes functionalities for fetching price data from Pyth and relies on key Solana and Metaplex libraries for its operations.

acte
Acte is a framework designed to build GUI-like tools for AI Agents. It aims to address the issues of cognitive load and freedom degrees when interacting with multiple APIs in complex scenarios. By providing a graphical user interface (GUI) for Agents, Acte helps reduce cognitive load and constraints interaction, similar to how humans interact with computers through GUIs. The tool offers APIs for starting new sessions, executing actions, and displaying screens, accessible via HTTP requests or the SessionManager class.

pocketgroq
PocketGroq is a tool that provides advanced functionalities for text generation, web scraping, web search, and AI response evaluation. It includes features like an Autonomous Agent for answering questions, web crawling and scraping capabilities, enhanced web search functionality, and flexible integration with Ollama server. Users can customize the agent's behavior, evaluate responses using AI, and utilize various methods for text generation, conversation management, and Chain of Thought reasoning. The tool offers comprehensive methods for different tasks, such as initializing RAG, error handling, and tool management. PocketGroq is designed to enhance development processes and enable the creation of AI-powered applications with ease.

inferable
Inferable is an open source platform that helps users build reliable LLM-powered agentic automations at scale. It offers a managed agent runtime, durable tool calling, zero network configuration, multiple language support, and is fully open source under the MIT license. Users can define functions, register them with Inferable, and create runs that utilize these functions to automate tasks. The platform supports Node.js/TypeScript, Go, .NET, and React, and provides SDKs, core services, and bootstrap templates for various languages.

client-python
The Mistral Python Client is a tool inspired by cohere-python that allows users to interact with the Mistral AI API. It provides functionalities to access and utilize the AI capabilities offered by Mistral. Users can easily install the client using pip and manage dependencies using poetry. The client includes examples demonstrating how to use the API for various tasks, such as chat interactions. To get started, users need to obtain a Mistral API Key and set it as an environment variable. Overall, the Mistral Python Client simplifies the integration of Mistral AI services into Python applications.

candle-vllm
Candle-vllm is an efficient and easy-to-use platform designed for inference and serving local LLMs, featuring an OpenAI compatible API server. It offers a highly extensible trait-based system for rapid implementation of new module pipelines, streaming support in generation, efficient management of key-value cache with PagedAttention, and continuous batching. The tool supports chat serving for various models and provides a seamless experience for users to interact with LLMs through different interfaces.

daydreams
Daydreams is a generative agent library designed for playing onchain games by injecting context. It is chain agnostic and allows users to perform onchain tasks, including playing any onchain game. The tool is lightweight and powerful, enabling users to define game context, register actions, set goals, monitor progress, and integrate with external agents. Daydreams aims to be 'lite' and 'composable', dynamically generating code needed to play games. It is currently in pre-alpha stage, seeking feedback and collaboration for further development.

mcp-framework
MCP-Framework is a TypeScript framework for building Model Context Protocol (MCP) servers with automatic directory-based discovery for tools, resources, and prompts. It provides powerful abstractions, simple server setup, and a CLI for rapid development and project scaffolding.

llm-sandbox
LLM Sandbox is a lightweight and portable sandbox environment designed to securely execute large language model (LLM) generated code in a safe and isolated manner using Docker containers. It provides an easy-to-use interface for setting up, managing, and executing code in a controlled Docker environment, simplifying the process of running code generated by LLMs. The tool supports multiple programming languages, offers flexibility with predefined Docker images or custom Dockerfiles, and allows scalability with support for Kubernetes and remote Docker hosts.

funcchain
Funcchain is a Python library that allows you to easily write cognitive systems by leveraging Pydantic models as output schemas and LangChain in the backend. It provides a seamless integration of LLMs into your apps, utilizing OpenAI Functions or LlamaCpp grammars (json-schema-mode) for efficient structured output. Funcchain compiles the Funcchain syntax into LangChain runnables, enabling you to invoke, stream, or batch process your pipelines effortlessly.

e2m
E2M is a Python library that can parse and convert various file types into Markdown format. It supports the conversion of multiple file formats, including doc, docx, epub, html, htm, url, pdf, ppt, pptx, mp3, and m4a. The ultimate goal of the E2M project is to provide high-quality data for Retrieval-Augmented Generation (RAG) and model training or fine-tuning. The core architecture consists of a Parser responsible for parsing various file types into text or image data, and a Converter responsible for converting text or image data into Markdown format.

educhain
Educhain is a powerful Python package that leverages Generative AI to create engaging and personalized educational content. It enables users to generate multiple-choice questions, create lesson plans, and support various LLM models. Users can export questions to JSON, PDF, and CSV formats, customize prompt templates, and generate questions from text, PDF, URL files, youtube videos, and images. Educhain outperforms traditional methods in content generation speed and quality. It offers advanced configuration options and has a roadmap for future enhancements, including integration with popular Learning Management Systems and a mobile app for content generation on-the-go.

aio-pika
Aio-pika is a wrapper around aiormq for asyncio and humans. It provides a completely asynchronous API, object-oriented API, transparent auto-reconnects with complete state recovery, Python 3.7+ compatibility, transparent publisher confirms support, transactions support, and complete type-hints coverage.

ElevenLabs-DotNet
ElevenLabs-DotNet is a non-official Eleven Labs voice synthesis RESTful client that allows users to convert text to speech. The library targets .NET 8.0 and above, working across various platforms like console apps, winforms, wpf, and asp.net, and across Windows, Linux, and Mac. Users can authenticate using API keys directly, from a configuration file, or system environment variables. The tool provides functionalities for text to speech conversion, streaming text to speech, accessing voices, dubbing audio or video files, generating sound effects, managing history of synthesized audio clips, and accessing user information and subscription status.

obsei
Obsei is an open-source, low-code, AI powered automation tool that consists of an Observer to collect unstructured data from various sources, an Analyzer to analyze the collected data with various AI tasks, and an Informer to send analyzed data to various destinations. The tool is suitable for scheduled jobs or serverless applications as all Observers can store their state in databases. Obsei is still in alpha stage, so caution is advised when using it in production. The tool can be used for social listening, alerting/notification, automatic customer issue creation, extraction of deeper insights from feedbacks, market research, dataset creation for various AI tasks, and more based on creativity.

ai-gateway
LangDB AI Gateway is an open-source enterprise AI gateway built in Rust. It provides a unified interface to all LLMs using the OpenAI API format, focusing on high performance, enterprise readiness, and data control. The gateway offers features like comprehensive usage analytics, cost tracking, rate limiting, data ownership, and detailed logging. It supports various LLM providers and provides OpenAI-compatible endpoints for chat completions, model listing, embeddings generation, and image generation. Users can configure advanced settings, such as rate limiting, cost control, dynamic model routing, and observability with OpenTelemetry tracing. The gateway can be run with Docker Compose and integrated with MCP tools for server communication.
For similar tasks

solana-agent-kit
Solana Agent Kit is an open-source toolkit designed for connecting AI agents to Solana protocols. It enables agents, regardless of the model used, to autonomously perform various Solana actions such as trading tokens, launching new tokens, lending assets, sending compressed airdrops, executing blinks, and more. The toolkit integrates core blockchain features like token operations, NFT management via Metaplex, DeFi integration, Solana blinks, AI integration features with LangChain, autonomous modes, and AI tools. It provides ready-to-use tools for blockchain operations, supports autonomous agent actions, and offers features like memory management, real-time feedback, and error handling. Solana Agent Kit facilitates tasks such as deploying tokens, creating NFT collections, swapping tokens, lending tokens, staking SOL, and sending SPL token airdrops via ZK compression. It also includes functionalities for fetching price data from Pyth and relies on key Solana and Metaplex libraries for its operations.

solana-ai-agents
JLB AI Agent is an innovative solution on the Solana blockchain that leverages artificial intelligence to automate complex tasks and enhance decision-making in the DeFi space. It offers real-time analytics, efficient operations, and seamless integration for both newcomers and experienced crypto enthusiasts. With features like autonomous trading, NFT management, DeFi insights, and comprehensive ecosystem integration, JLB empowers users with cutting-edge technology to navigate the dynamic landscape of blockchain.

JLB-AI-Agent
JLB AI Agent is an innovative solution built on the Solana blockchain that harnesses the power of artificial intelligence to automate complex tasks and optimize decision-making in the DeFi space. It aims to provide real-time analytics, efficient operations, and seamless integration for both newcomers and experienced crypto enthusiasts. The tool offers features like blockchain agent chat terminal, real-time streaming implementation, trading infrastructure, NFT management, AI integration, and more, empowering users with autonomous technology where AI meets the dynamic landscape of blockchain.

airswap-protocols
AirSwap Protocols is a repository containing smart contracts for developers and traders on the AirSwap peer-to-peer trading network. It includes various packages for functionalities like server registry, atomic token swap, staking, rewards pool, batch token and order calls, libraries, and utils. The repository follows a branching and release process for contracts and tools, with steps for regular development process and individual package features or patches. Users can deploy and verify contracts using specific commands with network flags.

goat
GOAT (Great Onchain Agent Toolkit) is an open-source framework designed to simplify the process of making AI agents perform onchain actions by providing a provider-agnostic solution that abstracts away the complexities of interacting with blockchain tools such as wallets, token trading, and smart contracts. It offers a catalog of ready-made blockchain actions for agent developers and allows dApp/smart contract developers to develop plugins for easy access by agents. With compatibility across popular agent frameworks, support for multiple blockchains and wallet providers, and customizable onchain functionalities, GOAT aims to streamline the integration of blockchain capabilities into AI agents.
For similar jobs

weave
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
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.

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

kaito
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
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
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
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
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.