A framework for continual learning and recursive self-improvement through harness adapter evolution.

[MLsys2026 Best Paper]: https://arxiv.org/abs/2506.08276. RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal d…

🦀 Rust API, 🐍 Python API, and 🤖 MCP Server for TP-Link Tapo smart devices

Give your AI agent a real browser — with a human in the loop. Open-source MCP-native browser agent.

Agent evals and guardrails as Jev decisions: one request per trace, a fraction of a cent, fast enough for the agent loop. Runs locally with Kev or Laya.

Every agent's model. One place. Codex on DeepSeek, Claude Code on Kimi, from the menu bar.

An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving

The ESP32-BlueJammer (Bluetooth jammer, BLE jammer, WiFi jammer, RC jammer) disrupts 2.4GHz communications. Using an ESP32 and nRF24 modules, it generates noise and unnecessary packets, causing int…

A lightweight, lightning-fast, in-process vector database

An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving

KeyForge3D is an app that turns a photo of a key into a 3D-printable STL file. Ideal for locksmiths and hobbyists, it analyzes the key's bitting pattern using image processing and generates an accu…

AIRecon is an autonomous cybersecurity agent that combines a self-hosted Large Language Model (Ollama) with a Kali Linux Docker sandbox and a Textual TUI. It is designed to automate security assess…

Zero-Shot Speech Editing and Text-to-Speech in the Wild

Repository for skills to assist AI coding agents with .NET and C#

AI agent framework for plan-first development workflows with approval-based execution. Multi-language support (TypeScript, Python, Go, Rust) with automatic testing, code review, and validation buil…

An open source design system that's fully customizable and agent ready

Point it at any web page and it finds the video, transcodes it, and streams it to your TV in real time. It even burns in subtitles.

Agentic AI security tool that applies proactive, attacker-first analysis directly to source code.

Bonsai Demo

#1 Persistent memory for AI coding agents based on real-world benchmarks

Open source observability platform for logs, metrics, traces, RUM (web, android, ios), Session replay, pipelines, SLO and LLM observability. A sophisticated, simple and highly performant alternativ…

OpenWiki is a CLI that writes and maintains agent documentation for your codebase.

TabFM (Tabular Foundation Model) is a pretrained tabular foundation model developed by Google Research for tabular data regression and classification.

Google Cloud Knowledge Catalog Tools and Samples

A generalist autonomous research agent — runs experiments, researches, and iteratively optimizes, autonomously.

Open-source BigSet — self-hostable live datasets populated by TinyFish web agents

An Open Source implementation of Notebook LM with more flexibility and features

A 7-layer memory operating system for Hermes Agent — persistent memory with Qdrant, structured facts, fabric recall, auto-curated wiki, and surgical context injection. Runs locally, any LLM provider.

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.