Git hosting, repos, issues and PRs.
viaSocket for your product and your coding agent: let your users connect any of 2,300+ apps, run actions and react to events; an AI assistant on any model with your endpoints as tools; AI memory per user; login, teams and organisations; automations per us
Deterministic local repository context, impact analysis, and merge-readiness evidence for AI agents.
Is this dependency still maintained? Scores npm, PyPI packages and GitHub repos 0-100.
Check whether a name is free on package registries, app stores, agent directories and domains.
CLI for AI loops for the SDLC on an existing git repo. Easy to set up, still powerful: agent loop campaigns (lumps) with CLI agents, git branches, and resumable LUMP marker commits
MCP security scanner and config linter for AI coding agents: finds exposed secrets, risky commands, broad permissions and invalid MCP servers in Claude Code, Cursor and VS Code (Copilot) configs. Local-first, no telemetry.
Design-system kit for coding agents: DTCG design tokens, 52 components, WCAG 2.2 AA→AAA + i18n/RTL accessibility, enforced single-theme consistency (contrast, hardcode, Tailwind-palette, theme-ref + CI gates), any-framework code, 2,144 design systems, 52
GitLab tools plugin for OpenCode - provides GitLab API access for merge requests, issues, pipelines, and more
Shared project memory for Claude Code, Codex and Cursor: decisions, corrections, overlap warnings.
MCP server + Agent Skill that brings OpenAI Codex's image generation to your coding tools, with a one-command installer for opencode, Claude Code, Codex, Cursor, VS Code, Gemini CLI and 20 more. Runs on your ChatGPT plan with no API key.
Turns an AI coding agent session into a reviewable Intent Document, validated against the diff.
Local-first context engine for AI coding agents. Pre-indexes your codebase into a dependency graph and feeds any MCP agent only the code that matters, so it stops rediscovering your repo before every change. Fable-5-level results from Opus 5 on SWE-bench
Automatic development memory for AI coding agents: turns your Claude Code, Codex, Gemini, Cursor, Copilot, Cline, Devin, OpenCode, Antigravity and Kimi Code sessions into structured commit summaries your agent can recall over MCP
Proof-carrying project memory with multi-language graphs, session receipts, exact recovery, relevant cited recall, provider usage accounting, and optional client-encrypted shared knowledge.
What a pull request's diff and its own tests show: one file, no dependencies.
Connect Claude Code or Codex to QApybara, the AI QA agent for pull requests, in one command.
Local-first MCP code intelligence: 37 tools — hybrid search, blast-radius, diff review, memory.
Your decisions, handed to your agents' sessions and held at the edits they govern: append-only and signed in the repository, and checkable by anyone.
Reusable AI agent prompts for development workflows with Jira integration — supports GitHub Copilot, Claude Code, and Codex
MCP Server with Code Review