Dev
GitHub repos gaining traction - what high-signal users are starring and what's climbing the board, captured daily and enriched from GitHub. Raw material for spotting new tech and patterns worth building on.
3,195
repos tracked
105
surfaced this week
193
created < 30d
Python
top language
63 repos
-
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, and collaborate in real time from any device.
-
A framework for few-shot evaluation of language models.
-
Learn harness engineering by building Claude Code from scratch. Free, open-source course: 8 articles, 6 videos, 1 codebase.
-
an rlm-style training harness
-
The ultimate setup harness for OpenClaw. Deploy in minutes. Stay running for months. No CLI required.
-
Multiplayer agent harness for work.
-
Local-first lab for testing AI agent workflows end to end: emulated Slack (signed events, buttons), local S3/SQS, deterministic authorization, and independent evidence instead of self-grading. Optional Google AX (Agent Executor) + Agent Substrate lane on GKE/gVisor, reported per assertion. Independent; not affiliated with Google.
-
A framework for building decision-model harnesses for any kind of task. Your program offers the model a short list of next steps, and the model picks one at a time until it can answer.
-
An open protocol and client for what your coding agents are doing: hooks for every harness, four privacy tiers, any sink.
-
The TypeScript framework for building composable actors around an immutable event log.
-
AutoSwarm: Unify Your Agents. Unify Your Context (Codex · Claude Code · DeepSeek Harness · Muse · Grok · WorkBuddy· nanobot · and more)
-
A Decentralized, Scalable Multiagent Harness
-
Evaluation harness for OpenHands V1.
-
An AI agent plays Baldur's Gate 3 on Linux through a Lua mod and an MCP server, seeing only what a player sees. Includes a model benchmark and a playthrough app.
-
Agentic AI security scanner that hunts exploitable vulnerabilities like an adversary, proves them with executable PoCs, and fixes them test-first. A maintained fork of Capital One's VulnHunter, rebuilt for any agent harness.
-
Examples and tests for Gemini API Managed Agents with Antigravity harness and sandboxes
-
Mirror is Reflection's coding harness
-
Feather agent harness, training integrations, and evaluation tools for knowledge work
-
RAX harness: coding agents that learn robot tasks by online exploration
-
A self-evolving personal OS
-
RetroAgent: Harnessing LLMs to Search Over Structured Memory for Agentic Retrosynthesis Planning
-
An Open Compiler Harness for Agentic GPU Programming
-
DeepSeek Harness: Everything is a Plugin.
-
An open protocol and client for what your coding agents are doing: hooks for every harness, four privacy tiers, any sink.
-
The ultimate harness for coding agents and beyond. All your agents. All your machines. One command center. Start with code, then follow your curiosity and build across disciplines: CAD, circuits, robots, games and music.
-
The agent-built terminal harness behind GPT 6 Astra's NetHack 3.6.7 ascension
-
Evidence-backed, model-agnostic runtime contracts for physical agents
-
Hosted, link-only submission site for the Sutro MNIST-medium time challenge on Modal, with the evaluator harness and a deployment runbook
-
Extensions for the Pi coding harness
-
Z.ai's coding agent harness. Powerful, intelligent, extensible.
-
Execution assurance agent guard and observability for autonomous AI operating in production.
-
Turn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more.
-
AgentSTAR: Agentic Shape Tracking and Reconstruction from Monocular Videos
-
Convert sessions across harnesses to a unified trajectory format - designed to be consumed by agents (e.g. for memory formation, dreaming, search)
-
Evaluation harness and tooling for measuring model compliance with the OpenAI Model Spec.
-
SoL-Pi: Scaling Auto-Research Loops for Efficient Agent Harnesses
-
The batteries-included agent harness.
-
civilization.sh — can AI civilizations beat Civ VI Deity++? Harness, live stream, replay, ladder. civilization.is
-
Public results and task definitions for FrontierHarness Eval
-
OpenCode vs Pi with extension
-
An MCP server that lets LLM agents play Civilization VI.
-
Speculative programmatic tool calling (sPTC) for harnesses like RLM, CodeAct, etc.
-
An open source agent microharness featuring persistent agency and recursive LLMs. Of bash, by bash, for bash; it's shells all the way down.
-
Clownfish is a maintainer codex harness for resolving clusters of issues identified in bulk at scale. 🐠
-
Give AI agents ambitious work without losing the plot. nac is an open-source harness for long-running tasks, using a central orchestrator, threads, and structured episodes to stay aligned with your intent.
-
extremely fast portable agent harness in c
-
Migrate coding agent sessions across 18 harnesses (Claude Code, Codex, Pi, OpenCode, Copilot, Antigravity, Vibe, Muse, Qwen, Kimi, Cursor, etc.)
-
Exo is an agent + harness architecture that is fully recursive, able to safely edit all aspects of itself at runtime to get better at your tasks.