Explore the directory

A tool that connects a live R or Python session in RStudio or Positron to Claude Code, Codex or another MCP-based LLM agent, letting the agent run code, see plots and edit files in that session.

• Editors

A self-hosted 2D visualization of AI agents as characters in a virtual office, showing what agents connected through OpenClaw or Hermes gateways are doing in real time.

• Coding agents
• AI evals

A deliberately vulnerable, CTF-style training platform for practicing attacks and defenses from the OWASP Top 10 for LLM Applications, in a scored range or against a real local model.

• Security

A Python library that acts as a drop-in replacement for LLM provider clients such as OpenAI, Anthropic or Gemini, compressing prompts to cut token costs while treating code and structured data as untouchable.

• Libraries

compressed-tensors is a library that extends the safetensors checkpoint format to store and load tensors compressed with quantization and sparsity schemes such as GPTQ, AWQ, SmoothQuant and SparseGPT in one unified format.

• Models
• Libraries

The Lean CLI is a cross-platform command-line tool for developing, backtesting, debugging and optimizing trading-strategy code against the open-source LEAN engine, locally or in the cloud.

• CLI tools
• Testing

An open-source platform for building, connecting and orchestrating AI agents powered by any local or cloud LLM, wiring agents and tools into pipelines meant to run predictably.

• Agent frameworks

A chat tool for exploring and understanding GitHub repositories or locally uploaded source trees using a local or hosted LLM, with a code graph for navigation.

• Agent memory
• RAG

A local-first AI filmmaking workspace controlled through Claude Code or Codex, combining filmmaking skills for scripts, images, video and voice with a visual canvas and timeline for organizing scenes and assets.

• Generative media

An agent framework built on LangGraph.js that adds file-system based routes, generated TypeScript types, workspaces, sandboxed execution and approval flows, for building agents in TypeScript.

• Agent frameworks

An open-source enterprise AI agent platform where agents onboard by reading project documentation, plan tasks, and execute them under their own identity and permissions, leaving an audit trail.

• Agent frameworks

ygot (YANG Go Tools) is a Go toolkit that generates Go structs and enums from YANG modules, validates populated structs against the YANG schema, and renders them to JSON or gNMI notifications for streaming telemetry.

• Libraries

A Rust and CUDA LLM inference engine tuned specifically for NVIDIA's Blackwell-generation GPUs (RTX PRO 6000, RTX 5090, B200), with an OpenAI-compatible server and hardware-specific low-bit quantization support.

• Inference

Volcengine's shared repository of over 100 official and third-party MCP servers, covering compute, storage, databases, containers, CDN, big data, video and security services, for its large-model ecosystem marketplace.

• MCP servers

A desktop app and built-in marketplace for adding and syncing Model Context Protocol server configurations across AI clients such as Claude Code, Cursor, VS Code, Cline and Windsurf, without calling any LLM.

• MCP servers

A Bun CLI that ingests Claude Code and Codex session transcripts, generates LLM-written daily summaries, and serves a browsable web journal with a calendar view and full-text search.

• Coding agents
• AI evals

KVDesk is a cross-platform desktop AI assistant that runs against local or remote OpenAI-compatible models, including vLLM, Ollama and LM Studio, with task planning, scheduled tasks and sandboxed code execution.

• Coding agents

Hibernate Tools is a set of tools that reverse-engineers Hibernate and JPA mapping artifacts from an existing database, and wraps that functionality as Ant tasks and Maven plugins for build integration.

• Databases

Plane's official Model Context Protocol server, giving an AI agent 30 tools across 207 operations to read and manage Plane projects, work items, cycles, modules, releases and customers.

• MCP servers

A pure-Rust, CPU-only, memory-safe OCR engine running a small zoo of hand-ported vision-language models, including a DeepSeek-OCR-derived model, a chart-data extractor and a sheet-music transcriber, with no Python, GPU or general ML framework required.

• Inference

A curated list of research papers on repository-level code generation and automated issue resolution, covering repo-level code completion, translation, unit-test generation, code QA and issue-task synthesis.

• Papers

A repository of runnable examples across many popular Python AI agent frameworks, configurable against GitHub Models, Azure OpenAI, OpenAI.com or local Ollama models.

• Tutorials

A no-code tool for building RAG applications by crawling websites or processing documents, then deploying to Vespa for hybrid search with an integrated chat UI and support for any OpenAI-compatible LLM.

• RAG

A set of hands-on Microsoft Learn exercises for building AI agents on Azure, covering common developer tasks and requiring an Azure subscription with quota for the necessary resources and models.

• Tutorials