Explore the directory

An open-source, self-hosted enterprise and site search server built on OpenSearch, with a web crawler for sites, file systems and databases, a REST API, and AI/RAG semantic search.

• RAG
• Databases

A small set of alternative output styles for Claude Code that change how it talks, not how it codes, trimming responses to plain, answer-first language for readers who find long output hard to follow.

• Agent skills

A PyTorch-like Python runtime for dynamic multi-agent and multi-session workflows, turning agent runtime state into explicit, composable objects such as Session, Sandbox, Memory, Tool, Agent and Workflow.

• Agent frameworks

A frozen but still-working, compressed spec-driven-development plugin for Claude Code that runs one durable spec file through a grill, spec, research, review and build loop with no sub-agents.

• Agent skills

A local-first document redaction workbench that finds and anonymizes sensitive information in PDFs, scans, Office files, images and text using local LLMs and vision-language models.

• Security
• Data engineering

A curated personal library of Agent Skills, plus a CLI and TUI for building and managing a skill library of one's own, for any Agent Skills-compatible coding agent.

• Agent skills

A collection of more than 80 runnable Python examples for building autonomous AI agents and multi-agent systems with uAgents, ASI:One, Agentverse, MCP, A2A, LangChain, CrewAI and other frameworks.

• Agent frameworks
• Tutorials

A unified terminal UI and CLI that indexes and searches local session history from more than two dozen coding agents and AI chat tools in one searchable timeline.

• Coding agents
• Agent memory

A harness that coordinates a team of coding agents and their human reviewer through one pipeline, where agents propose work and humans verify it before it ships.

• Coding agents

An AI-native browser automation engine for autonomous agents, offering both zero-token deterministic extraction and LLM-driven extraction at large scale, controlled by a Rust CLI and MCP.

• Browser automation

A self-hosted web UI for more than 30 kinds of generative AI, including image, audio, video and chat models, able to run offline on modest hardware without a dedicated GPU.

• Inference
• Generative media

A desktop MCP client and local AI playground that lets a user chat with cross-vendor LLMs through the Model Context Protocol, with no required account and full local control.

• MCP servers
• Inference

A 100% open-source, MIT-licensed AI coding agent designed to match Claude Code's capability at a lower token cost, using bring-your-own-key access to any OpenAI-compatible model.

• Coding agents

A model-neutral MCP server that gives any AI chat client or agent safe access to a codebase, with file editing, command execution, git, and permission-gated sandboxing.

• Coding agents
• MCP servers

A containerized, reproducible Docker development environment for running Claude Code with pre-configured language profiles, per-project isolation, and MCP servers.

• Coding agents
• Containers

A toolkit that gives an AI coding agent both the MCP tools and the Model-Based Design knowledge to read, build, edit and test Simulink models correctly.

• MCP servers
• Agent skills

A curated list of open-source tools that automate scientific research, spanning literature review, idea generation, experiment execution, paper writing and peer review.

• Curated lists

An MCP server that adds structural code navigation, persistent memory, and safer Bash command rewriting to AI coding agents, aiming to cut the tokens and time a coding task needs.

• MCP servers
• Agent memory

A Chrome extension that runs an on-device AI assistant entirely in the browser with WebGPU and Transformers.js, letting it manage tabs and answer questions about the current page.

• Inference
• Browser automation

A set of curated Agent Skills that give Claude Code and Codex reasoning-first expertise across 18 core AWS services, kept current with weekly documentation checks.

• Agent skills
• Hosting

A research system and reference implementation of the VINDEX3 format for executing, representing and studying a machine learning model as an inspectable, queryable artifact.

• Models

A vLLM engineering fork focused on making modern large language models run fast on older NVIDIA Tesla V100 (SM70/Volta) GPUs, rather than merely able to start on them.

• Inference

A collection of AI agent projects, framework tutorials and integrations, covering AutoGen, CrewAI, PydanticAI, Smolagents and the OpenAI Agents SDK, used as the code hub for a YouTube channel.

• Tutorials

A multi-model DBMS supporting SQL, Cypher, Gremlin, HTTP/JSON, MongoDB, and Redis query interfaces over graph, document, key-value, time-series, and vector data in one engine.

• Databases