Explore the directory

A unified agentic framework for long-horizon, autonomous scientific discovery, covering hypothesis generation through automated experimental execution across physical, biology, earth and life science domains.

• Agent frameworks

An AI agent harness that can inspect and safely edit its own code, prompts, memory and tooling at runtime, so it can incrementally improve itself and even manage a lineage of its own clones.

• Agent frameworks

A research method, from Microsoft, for augmenting a language model with an external knowledge base without a separate retrieval step, so the added computation grows linearly rather than quadratically.

• Models

A benchmark of 113 original, long-horizon software-engineering tasks across five languages, drawn from active open-source repositories, for measuring how well frontier coding agents perform on real engineering work.

• AI evals

A fork of ClawTeam that coordinates a swarm of CLI coding agents, with OpenClaw as the default agent, so a single goal is split into tasks, assigned to spawned worker agents, and merged back together.

• Coding agents

A JavaScript SDK that runs large language models, speech recognition, text-to-speech and audio separation directly inside the browser using WebGPU, with no server required.

• Inference
• Speech

A curated, timeline-organized list of open-source and other software that combines large language models with web search, such as chat with follow-up questions and agent-driven research tools.

• Curated lists

A drop-in compression proxy that sits between a coding agent and its LLM API, stripping tool-schema bloat and compressing tool results and stale history to cut input-token bills without changing the agent.

• Coding agents
• LLM gateways

An open-source observability workspace that ingests OpenTelemetry traces, logs and metrics, groups noisy signals into incidents, and uses AI agents to investigate and help self-heal production issues.

• Agent frameworks
• Monitoring

A terminal dashboard for creating, editing and monitoring cron jobs on local and remote servers over SSH, built with Textual.

• Terminals
• CLI tools

A self-hosted enterprise knowledge hub and MCP server that compiles an organization's documents into a structured, permission-scoped wiki that Claude and other LLMs can query.

• MCP servers
• RAG

A setup and operations harness for OpenClaw deployments, adding a guided setup wizard, a self-healing watchdog and multi-agent management on top of the OpenClaw gateway.

• Agent frameworks
• Hosting

A Chinese medical question-answering system that combines a Neo4j knowledge graph of diseases with BERT-based entity recognition and a local LLM, using structured graph retrieval instead of a vector database to reduce hallucination.

• RAG
• Databases

An embeddable, ACID-compliant Datalog database built on a fork of LMDB, offering Datomic-style queries with a cost-based query optimizer and full-text and graph-style search.

• Databases

An open-source alternative to xAI's Grok Bot that runs always-on AI bots on the user's own machine, turning a described workflow into a microapp with a human approval gate on every external action.

• Coding agents
• Workflow automation

An AI co-worker, built on the Claude Agent SDK, that runs on its own dedicated machine, keeps persistent memory across sessions, and can install software, build tools and add its own communication channels.

• Agent frameworks
• Agent memory

An MCP server that gives an AI client access to Brave Search, including web, local business, place, image, video and news search, plus AI-generated summarization.

• MCP servers

A kit of instructions, design tokens and runnable skills that turns an AI coding agent into a design-system generator, checked against dozens of automated accessibility and consistency gates.

• Agent skills
• Design tools

A VS Code extension that adds DeepSeek V4 models to the GitHub Copilot Chat model picker, so a user keeps Copilot's agent mode and tools while paying DeepSeek directly for inference.

• Editors

A Model Context Protocol server that connects LLMs such as Claude, GPT and Gemini to ROS robots for two-way communication, without changing the robot's existing source code.

• MCP servers

An open-source hardware guide, with parts lists, CAD and assembly photos, for building your own local machine to run large language models instead of renting inference from a cloud provider.

• Inference
• Tutorials

A Model Context Protocol server that lets AI agents create, inspect and edit Draw.io diagrams, such as architecture diagrams and flowcharts, through a built-in editor or a browser extension.

• MCP servers
• Design tools

A CLI tool that generates configuration files for many AI coding tools, such as rules, commands, MCP settings, ignore files and skills, from one unified set of AI rule files.

• Coding agents
• CLI tools

A collection of PHP_CodeSniffer sniffs that improve the safety and behavior of PHP code, detect dead code, and enforce consistent formatting.

• Code quality