Stars
Benchmark for tracking model capability after release.
petals carries your brand into everything a coding agent builds, and checks what came out: colours, type, layout, surface, voice and content, as SARIF. A skill plus deterministic scripts, no server.
Conducted: a local-first desktop app for running coding agents in parallel, each in its own git worktree.
DesignCraft: An open-source page and layout design editor written by scratch in pure Rust
Procedural risograph films in single HTML files (Window Seat, Roost and more), with the Claude Code skills, docs and tools to make your own.
pleach — deterministic conductor for DAGs of verified agent work (tend2 plans it, pleach runs it, umbel drives the workers)
Claude Code plugin that replaces the compaction summary with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, everything kept stays verb…
plotplot, the umbrella: brand, law, contracts and the map of the garden
The judge of the diff: a static binary that reads what an agent produced and refuses dishonest growth, as SARIF, in milliseconds.
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.
Memory library for building stateful agents
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context
All parts of Claude Code's system prompt, 27 builtin tool descriptions, sub agent prompts (Plan/Explore/Task), utility prompts (CLAUDE.md, compact, statusline, magic docs, WebFetch, Bash cmd, secur…
Convert plain-English problem description into a Timefold solver prototype
Cost per correct answer — a neutral, reproducible, verifiable benchmark for CLI-based coding agents
Remote-control interactive agent CLIs (Claude Code, Codex, Gemini) over tmux. One binary, three faces, one provider abstraction.
Open-source e-reader firmware
The most complete open-source travel planner: real-time collaboration, bookings, budgets, packing lists, journals, offline PWA, SSO and an AI-ready MCP server, with planet-wide place search and rou…
your personal encyclopedia, written by agents
peer messaging between AI agents, with a human at the gate — one file, zero dependencies.
marwey / mrkd
Forked from jahala/mrkdA native macOS markdown viewer with iTerm2/vscode theme support
Vision Wormhole: Latent-Space Communication in Heterogeneous Multi-Agent Systems
A native macOS markdown viewer with Finder quick look and iTerm2/vscode theme support
Plan, build and review software with your coding agents. Work side by side in the App or browser, or use your favourite terminal or IDE.
Shared Single-file memory layer for all your agents, sub mili-second RAG over text, photo and video on Apple Silicon.. No Server. No API. One File. Pure Swift
Self-updating articles concept using polyglot html/bash files. No server, no db. The file is the app.
Smart code reading for humans and AI agents. Definitions, callers, dependencies and function-level diffs from tree-sitter. One binary, no index. MCP server + CLI. Install: cargo install tilth or np…
Store your data from all your accounts and devices in a single cohesive timeline on your own computer