The open-source context layer for AI agents and enterprise AI search. Permission-aware search and cited answers across Slack, Drive, Jira, GitHub, Microsoft 365 and 35+ sources, for people and agen…

Patchmill is an agent-driven software factory

Lightpanda: the headless browser designed for AI and automation

A mobile web RTS

Presentation Slides for Developers

Dataset and benchmark for RAG on company internal documents.

Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and multimodal RAG on embedded LanceDB, with Docling parsing and an MCP server

Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per re…

Release-aware Python source transpiler and capability discovery for Monty

SoL-Pi: Scaling Auto-Research Loops for Efficient Agent Harnesses

Monkey patch, test, and trace Python by attaching bindings to call sites, without modifying the code being observed. Built on wrapt.

A plate solving telescope finder based around a Raspberry PI and RPI HQ Camera

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, an…

Single-pass SSA compiler and tiered register VM for a sandboxed Python subset, with NaN-boxed values, inline caches, memoization, mark-sweep GC and snapshots. One WebAssembly module runs in browser…

Official Repository of MMLONGBENCH-DOC: Benchmarking Long-context Document Understanding with Visualizations

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

Prompt & context power tool for agentic work

Bash for Agents

Dart binding for pydantic/monty

The fast, precise document-intelligence engine for every language: text, tables and metadata from 100+ formats, with OCR, transcription and code intelligence.

Send push notifications to your phone or desktop using PUT/POST

A codesigning tool for Python packages

Secure, Fast, and Extensible Sandbox runtime for AI agents.

Optimize prompts, code, and more with AI-powered Reflective Optimization

Skill-powered AI agents implementing the Agent Skills specification with pydantic-ai

Develop web components visually with testing and docs.

A secure Python sandbox, written in Rust, for code written by AI.

Open-source, self-hosted Claude Code - a terminal AI assistant and the Python framework behind it. Tool-calling, sandboxed execution, multi-agent teams, skills, checkpoints, unlimited context - on …

Agent skills for Obsidian. Teach your agent to use Obsidian CLI and open formats including Markdown, Bases, JSON Canvas.