AI & Agents MCP servers

Autonomous spec-to-product coding-agent CLI with an MCP server exposing 39 tools over stdio.

Multi-model rating for AI evaluation. Agreement is reliability, not validity. Maintenance mode.

Submit a tool to the Altimateguide directory for editorial review.

Coding agent memory — one local MCP server for every project. Warns before repeating failed fixes.

MindQL queries, hybrid search, and a thought graph - read/write memory for AI agents.

Tamper-evident decision audit trail and outcome-weighted memory for AI trading agents.

Expose the 5dive agent-fleet CLI (tasks, agents, digest) as MCP tools, over stdio or HTTP.

Memory for any Ai: remembers across sessions, enforces your rules before actions, reviews the work.

One MCP server bridging the Codex, Cursor, OpenCode, Claude, and Antigravity CLI agents

FCoP Core adapter with 25 canonical tools and 6 read-only resources for durable agent work.

Multi-model AI brainstorming debates with code review and quick perspectives

MCP server for BasedAgents, the task marketplace for AI agents: claim paid tasks, get paid in USDC.

Mine your AI coding session logs into a you.md profile with dated receipts, for an agent to read.

Read, replay and fork recorded coding-agent runs.

Auditable multi-agent coordination: fleets, P2P messaging, witnessed receipts, quorum.

Finds transitive excessive agency across LangGraph/CrewAI/AutoGen orchestration graphs

Seeds, governs and navigates a memory_bank knowledge base: gated writes, routing, drift vs code

MCP server that checkpoints long agent tasks: roll back to any step, resume in a new session.

Multi-model AI gateway — 10 providers including Cloudflare and Vercel, with conversation memory.

Sits in front of any MCP server. Reads pass, writes are checked against your lists.

Local MCP framework for bounded cross-model delegation, routing and evidence verification.

Local memory your AI tools share: decisions, notes and corrections that carry across sessions.

Tamper-evident memory + governance MCP for Claude Code, Cursor, Codex. Ships the Seatbelt kit.

Read and verify the Blue Cloud Cyber agent guestbook, and sign one Ed25519 entry per UTC day.

Memory that knows when a remembered fact has been replaced, not just when it was written.

Verify that an agent's claimed outcome actually happened, using independently gathered evidence

Local MCP runtime for coordinating Freebuff, Codex, OpenCode, Claude Code, and Cursor agents.

Detect stale source context and retain traceable code-chain understanding for AI coding agents.