tigerless-labs/autoharness
Autoharness — a self-learning skill layer for Claude Code — distills skills from your real sessions, updates them as you work, and prunes the ones that stop getting used. No daemon, no benchmark.
Language:Python
Total stars: 2924
#python
#agentskills, #claudecode, #claudecodeplugin, #llmagents, #python

sapientinc/PRAXIST
Autonomous research system for measurable, computer-executable research.
Language:Python
Total stars: 6786
#python

pathwaycom/arc-task-gen
Generates original ARC-AGI-1-style tasks distribution-matched to the public eval set.
Language:Python
Total stars: 11243
#python

abi/screenshot-to-code
Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue)
Language:Python
Total stars: 78317
#python

cloud-in-a-bottle/cloud-in-a-bottle
Deploy, use, and share web apps on a server you control. Your apps, data, and infrastructure stay yours.
Language:Python
Total stars: 971
#python
#appplatform, #containers, #deployment, #homeserver, #paas, #personalcloud, #personalserver, #selfhosting

Farama-Foundation/Shimmy
PettingZoo and Gymnasium bindings for popular reinforcement learning environments outside of Farama
Language:Python
Total stars: 945
#python
#deepmindcontrolsuite, #deepmindlab, #gymnasium, #gymnasiumenvironment, #reinforcementlearning

redhat-et/ripwire
The ripgrep of AI context: a zero-dependency C++23 CLI + MCP server for coding agents. Find what you want without reading the repo, then check you built what you meant — blast radius, tests-to-run, quality deltas. Signatures at 74.7% fewer bytes than bodies; every guess labelled, every loss published. Paddle out with a map.
Language:C++
Total stars: 1782
#cplusplus
#aiagents, #callgraph, #claude, #claudecode, #cli, #codenavigation, #codex, #codingagents, #contextengineering, #cpp, #developertools, #llm, #mcp, #mcpserver, #python, #rust, #staticanalysis, #swift, #treesitter, #typescript