#claude

Capture a logged-in browser task once — replay it forever at zero LLM tokens. Local-first browser-automation MCP for Claude Code, Cursor & any MCP host; credentials never leave your machine.

Ask your repo what breaks before an AI coding agent edits it.

El repositorio no publica descripción.

Opinionated full-stack framework for Convex + Expo apps

🪛 A CLI tool for everything that is needed in a day to day software development basis

Self-tuning multi-agent AI trading system. 8-source signal fusion, Bull/Bear/Judge debate on Claude Opus 4.7, Kelly + ATR position sizing. Python · Kalshi + Polymarket adapters.

Go-only, report-first code scanner exposed as an MCP server. Indexes a module, runs deterministic analyzers, and reports genuine bugs, dead code, stale docs & outdated APIs — never editing your code until you ask.

El repositorio no publica descripción.

Give coding agents a disposable Linux VM, not your laptop

Make Claude Code and Codex prove their work — runs advance only when your tests, lint, and typecheck actually pass. Open-source Go runtime.

Local-first workspace for running, organizing, and monitoring Codex, Claude Code, Aider, AGY, OpenCode, and shell sessions.

CLI that ranks which AI coding subscription quotas to burn before they reset (use-it-or-lose-it)

A typed maintenance surface for the Claude Code harness — the Rust of agentic harnesses: declare a contract, gate on conformance.

The context mesh for autonomous agents — unified observability, telemetry, and inter-agent coordination https://fmicalizzi.github.io/moolmesh/

Observe your Claude Code sessions across machines — a read-only monitor (TUI + web). The lookout watches and signals, never steers.

Todo and task management

AI-powered Git copilot for your terminal. Talk to Git in plain English, automate commits, review code, and manage repos with a beautiful TUI.

Open source memory library for AI agents

Persistent, verified memory for coding agents — so they stop re-explaining your codebase and never act on stale knowledge. Every memory is checked against your actual code; lives in your repo as plain files, shared via git. No account, no DB. Install: npx -y @kage-core/kage-graph-mcp install

Rust interfaces to the streaming code protocols.

MCP server for Scholar Sidekick — resolve any scholarly identifier (DOI, PMID, PMCID, ISBN, arXiv, ISSN, ADS, WHO IRIS) into 10,000+ CSL styles or nine export formats, single or batch.

Customizable status line formatter for Claude Code CLI, written in Go

TypeScript harness for building personal AI agents with durable memory — agents that live across your channels (CLI, Teams, iMessage, mail, voice), use real tools, and stay coherent across turns. The runtime behind @ouro.bot.

Self-healing browser QA: natural-language scenarios verified by an AI agent, replayed deterministically in CI

El repositorio no publica descripción.

El repositorio no publica descripción.

Stream Claude Code's hidden output (thinking, tool calls, subagents) to a separate terminal in real-time

Fuzzy-search Claude Code conversation history

CLI and MCP server for C2PA / Content Credentials provenance: report what a file claims, or fully verify it — COSE signature, certificate chain, hash bindings, RFC 3161 timestamp. Reads JPEG, PNG, WebP, GIF, TIFF/DNG, HEIC, AVIF, SVG, MP4, MOV, AVI, WAV, MP3 and PDF. Wraps github.com/richardwooding/c2pa.

A governed, local-first MCP development control plane for AI coding agents.