- Conduid
- Marketplace
- #agent-loop
MCP servers tagged agent-loop
16 live MCP servers tagged "agent-loop", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with agent-loop.
Lexora
A self-evolved, sovereign desktop AI agent built for real-world action — beyond model wrappers and coding copilots. / 真实实践中自我演化的独立桌面 AI Agent。
Tma1
Local-first observability your agent reads back. TMA1 records every LLM call, then routes what it sees into the agent's next turn via hooks and MCP.
Athena Loops
MIT-licensed, backend-agnostic AI agent orchestration loop in Python: orchestrator→worker→reviewer as a deterministic harness. Drive coding-agent backends through an MCP server +…
Sruja
A CLI-first autonomous coding agent where the actor never grades itself. Every edit is grounded in your repo's real topology and verified by an independent deterministic grader (d…
Nexus
Nexus — AI Coding Agent Desktop App. Free, local, open source. Actually builds things — not just chat about them.
KairoCode
Terminal AI Coding Agent prototype with Agent Loop, MCP tools, permission guardrails, memory, and multi-agent collaboration.
Smoke Monkey Harness
Open source AI agent harness & agentic AI runtime in TypeScript. 6-phase state machine, 24 tools, human-in-the-loop permissions, MCP server, and composable agent APIs. Zero depend…
Os Loop Skills
Official skill marketplace for OS Loop AI: installable, composable TypeScript skills that extend agents with tools, workflows, and real-world capabilities
Diffgate
Verify declared code edits against tree-sitter structural differences and expose deterministic verdicts through CLI or MCP.
PsChina/deepseek-as-subagent
platform installer.
Awesome MCP Registry
AI-curated, self-updating directory of MCP servers. Discovered from GitHub & the official registry, analyzed and ranked by AI weekly.
Claude Goal
Goal-bounded autonomous turns for Claude Code — set an objective, set a budget, walk away. Stop-hook continuation engine + tool-equipped completion evaluator.
Learn MCP Agent Loop
An MCP host that owns the agent loop - a Next.js chat app that picks tools across multiple MCP servers, calls them, and loops until done
Learn MCP Agent Ledger
Project #5 in a learn-MCP series: sampling, where the server borrows the host model instead of holding its own key. Adds a cost ledger, spend gates, and replayable runs so every m…
Autonomous Agent Nightshift
Claude Code skill + npm CLI for running AI agents overnight on your codebase. Write todo with Implementation+Validation pairs, hit launch, wake up to validated code. 6 slash comma…
Learn MCP Agent Guard
An MCP host that stops and asks before it does anything it can't undo: Postgres persistence, human-in-the-loop approval gates, evals, and replay.