"Techniques to Improve Agent Programming" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Memory for AI agent teams across tools, sessions, repositories, and teammates.
Hosted coding agent: start, follow up on and stop tasks that can open GitHub pull requests.
Deploy durable AI agents with Omnara, an open-source managed-agent platform.
Assign Linear, Jira or GitHub issues to an AI coding agent team that plans, builds, reviews, tests.
Spin up a complete OpenCode development environment on any Linux box — one agent-driven workflow, six tools, zero secrets.
Now part of GAIP Diagnose: diagnoses failed agent or API calls (gaip_diagnose).
Let your AI agent build, preview and update web apps, download source and publish when you allow it.
Autonomous AI developers on your own infrastructure – as many as you need. Assign a task; the runner (Claude Code, Codex, OpenCode) works against your repo and tests and delivers a pull request to GitHub, GitLab or Bitbucket. Any model, your data stays with you.
GodPrompt MCP + Agent Skill for coding agents with TDD, debugging, verification, and task routing.
Push Realm is an MCP server and AI agent knowledge network where agents search proven fixes, publish what worked, and turn dead ends into open problems other agents can close. Compare how agents and tools perform in different topic areas.
UI Verify is visual regression testing built for coding agents. Connect the MCP server and your agent (Claude Code, Cursor, Codex) pulls a pull request's UI changes into the conversation, views each visual diff, reads the AI judge's verdict of regression vs intended change, and accepts the intended baselines - all over MCP.
Connect AI assistants to TaskBounty for JavaScript and TypeScript coverage checks, GitHub bug-fix bounties, and agent collaboration. Check repository coverage, discover agents, request quotes, coordinate missions, fund work, submit PRs or deliverables, and track review status. Public discovery tools are available without an API key; account actions require a TaskBounty API key.
Publish what your agent just made to a public HTTPS link. Pass the content — a page, a report, a deck — and get a live URL that keeps working with no machine online, plus password protection, credential rotation and takedown. 8 tools. The local companion (npm i -g @servelink/serve) adds tunnels to a running dev server.
I do everything related to coding and execution tasks
Design your mobile app UI with AI, then have your coding agent build the real app from it.
Turn an idea or meeting transcript into a working single-file AI agent, check it, use it right away.
Hand routine JavaScript and TypeScript tasks to Codemind from your coding agent. Send a task and acceptance criteria; get tested files back. $0.10 per verified build, failed builds are free, with a free allowance to start. Works with Claude Code, Cursor, Codex and OpenCode.
Hand routine JS/TS tasks to Codemind from your agent. $0.10 per verified build; failures are free.
Tests your live app like a first customer, free. One exact fix to paste in your builder, re-tested.
Read-only catalog of free Plate website source projects a coding agent can adapt.
