developer tools

Shed is a GitHub-hosted CLI for managing read-only repo catalogs and disposable writable workspaces for terminal coding agents. It syncs fresh checkouts, supports parallel agent sessions, and integrates with Claude Code, Cursor CLI, and opencode.

GIDE is a privacy-first AI coding command center that runs local or cloud models in a code editor and terminal. The page shows live session examples, a write-approval gate, CLI support, and an OpenAI-compatible local API.

Local code-context engine for AI coding agents. It indexes TypeScript, Python, or Swift repositories into a symbol-level graph in SQLite and exposes MCP tools for symbol lookup, impact analysis, and graph queries.

Itsuki is an open-source memory layer for AI tools and agents. It offers a single key and structured, source-linked memories across assistants, coding agents, workflows, SDKs, REST, and MCP integrations.

Notula is a WYSIWYG Markdown editor for docs-as-code, built around repositories that AI agents and humans both edit. It supports comments, review threads, background git sync, and desktop apps for macOS and Windows.

A zero-setup service for testing magic-link sign-in flows with disposable inboxes and a simple no-auth API for coding agents.

A CLI that turns websites into compact, numbered views for AI agents so they can browse pages with far fewer tokens. It includes install steps, command examples, supported sites, and benchmark notes.

LLM Status scans codebases to find where AI models are used, tracks retirement and deprecation dates, and can warn in CLI, CI, GitHub App, or alerts. It also offers replacement suggestions and a fix flow that rewrites model IDs.

Leviath is a Rust-based agent runtime for running structured LLM agents from a single file. It emphasizes context regions, stage-specific models and tools, run journaling, live steering, and the ability to run many agents in one process.

MathCode is a terminal AI coding agent for mathematical formalization: it turns plain-language math problems into Lean 4 theorems and attempts formal proofs, with a persistent Lean REPL and supporting theorem/axiom libraries.

Parley is coordination infrastructure for autonomous coding agents. It lets agents hand off work asynchronously, records each relay in an append-only flight recorder, supports escalation, soft file-locking, and works with Claude Code, Cursor, Codex, Copilot, Antigravity, and any MCP client.

Ambient macOS light strip for AI coding agents. Shows agent state beside the Dock with eight virtual LEDs and supports publishing status over a local CLI/API.

Doubt is an open-source, zero-dependency CLI and Agent Skill for turning contested questions into source-grounded evidence maps with supports, contradictions, unknowns, and portable HTML output.

A local-first TypeScript toolkit for crash-testing AI agents and MCP servers, replaying failures deterministically, and turning broken traces into regression tests.

A local merge queue for parallel Claude Code agents that serializes landings, builds, and test runs to avoid push races and shared-resource flakiness.

Headroom is a macOS menu bar app that compresses noisy prompt context before it reaches Claude Code and Codex, aiming to cut token usage by about 50% while keeping the original retrievable on demand.

cloro is an API for scraping and structuring results from search and AI search surfaces like ChatGPT, Gemini, Perplexity, Copilot, Google Search, and AI Overview. The page shows request and response examples, supported models, pricing tiers, and claims of parsed markdown, sources, and citations.

A public MCP server from PixelGust that lets Claude, Cursor, and other MCP clients query live weather, forecast, climate history, terrain, fire risk, flood susceptibility, and related environmental data.

A 30-second WebGPU benchmark that measures a device’s memory-bandwidth ceiling for local AI and checks for a WebGPU subgroup correctness bug, with receipts, projections, and comparison data.

CodeTrain is a hands-on AI coding trainer that teaches developers on their own codebase by making them write each step themselves, with hints, test runs, and progress tracking.

Aloud is a macOS tool that reads Claude Code and OpenAI Codex replies out loud using local text-to-speech. It includes session-level controls, keyboard shortcuts, hook integration, and a clear install flow for developers.

API-first uptime monitoring with REST, GitHub Action, and MCP support so developers and AI agents can create monitors, check status, and route incidents from the tools they already use.

Coasty is a computer-use API for running autonomous tasks on managed Linux or Windows machines, building multi-step workflows, and dropping down to lower-level prediction primitives when needed.

Open-source self-hosted voice AI agent for Asterisk/FreePBX with Audiosocket/RTP support, a modular STT/LLM/TTS pipeline, and quick-start docs for deployment.