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.

Dataset and benchmark for RAG on company internal documents.

Prompt & context power tool for agentic work

Bash for Agents

Dart binding for pydantic/monty

Polyglot document intelligence with a Rust core: extract text, metadata, images, tables, and structured data from 106 formats across 140 file extensions, plus code intelligence for 371 languages. F…

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

A Sigstore client written in Python

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 minimal, secure Python interpreter written in Rust for use 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.

Task Planning and Tracking toolset for Pydantic AI agents, enabling hierarchical task management with subtasks, PostgreSQL storage for multi-tenancy, and an event system for webhooks and callbacks.

A modern static site generator by the Material for MkDocs team

The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval

Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code

Hindsight: Agent Memory That Learns