An agent that compiles git maintenance chores into reusable programs, then decides whether to replay them by running checks rather than by guessing the task looks familiar
- agent-architecture
- git-automation
- llm-agents
- program-synthesis
132,241 visible repositories in the index
1,201–1,224 of 1,346 · Most stars
An agent that compiles git maintenance chores into reusable programs, then decides whether to replay them by running checks rather than by guessing the task looks familiar
Reusable GitHub Actions source builds for jhaizhou-ops/d2r-mobile. Bring your own prepared game archive.
Open-source AI navigation glasses under $35 — they say what they see, and say 'uncertain' instead of guessing. Safety-first, printable enclosure, community build kit.
Iterative Linear Quadratic Regulator with auto-differentiatiable dynamics models
A clean home screen for LG webOS. No root. No always-on computer. On-TV Home-button helper, a customizable app grid and dock, and a way back to LG Home.
A highly customizable DIY irrigation/sprinkler controller based on Raspberry Pi
Easily retargetable and hackable interactive disassembler with IDAPython-compatible plugin API
scalable audio processing framework and server written in Python
KnoxMap: turn any real place into a playable Project Zomboid Build 42 map (built on Knoxify)
Compile organizational policy into verifiable decision training data.
Code for the paper “The Alien Space of Science: Sampling Coherent but Cognitively Unavailable Research Directions”
OpenAI-compatible async gateway for muse.ai with pluggable drivers (mock / browser-CDP / http)
a parametric variable font by David Berlow
FOREST is a research agent for long-horizon science, where evidence gets lost, errors compound, and goals drift. It explores ideas, reads literature, forms hypotheses, runs real experiments, analyzes results, revises paths, and builds a full paper—all in an editable graph you can inspect, branch, redirect, with claims and figures linked to evidence
NNDial is an open source toolkit for building end-to-end trainable task-oriented dialogue models. It is released by Tsung-Hsien (Shawn) Wen from Cambridge Dialogue Systems Group under Apache License 2.0.
PyC (Pytorch Concepts) is a PyTorch-based library for designing concept-based interpretable deep learning models.
Python installable command line utiltity for mitigation of host and key compromises.
Self-improving code for any git repo: give it a measurable goal, a coding agent (Claude Code or Aider) proposes changes, the kernel scores them, keeps winners and rolls back failures. Open-source AlphaEvolve / FunSearch-style evolution loop, sandboxed, with an auditable ledger.
TranslatedTask-package workflow for AI coding agents with verifiable scope, evidence, and Git gates.
Generative Fill, Remove object, Generative Expand and Text to Image for PhotoCraft and GIMP 3. Free, local, on your own GPU through ComfyUI.
A decision-model-based ontology & knowledge-graph builder — builds governed knowledge graphs from your documents, every fact gated and traceable to its evidence.
Solve automatic numerical differentiation problems in one or more variables.
Self-hosted web control room for Claude Code: persistent sessions, memory, scheduled jobs, Telegram and voice on your own server. Free and fair source (source-available).
Belay is a python library that enables the rapid development of projects that interact with hardware via a micropython-compatible board.