FIVE Persona Engine
Local installio.github.kiro0x/five-mcp
160K deductive JSON persona constraints. 0 drift breaks in 120 turns. Free API, no key.
2,187 servers in AI & Agents
160K deductive JSON persona constraints. 0 drift breaks in 120 turns. Free API, no key.
Local deterministic project memory for AI agents with context packs, gates and checkpoints.
The immutable delegation frame for AI agents: gate any sensitive action, human-in-the-loop.
Local MCP gateway daemon: route, audit, and inspect MCP servers from one config.
B2A2H MCP server — AI agent app store. Auto-discover and recommend MCP servers for any project.
Delegate coding and sysops tasks to cheaper agents or local LLMs via durable background job queues.
Publish structured, AI-readable business identity data as an MCP server in minutes.
MCP server that nudges better AI session behavior through token usage and efficiency analysis
Structured observability for AI agents. Trace steps, decisions, and errors. MCP server + CLI viewer.
Persistent AI memory using orbital mechanics. 100% local, zero API keys, MCP-native.
MCP server providing personalized greetings with AI-powered tools using Spring Boot and Spring AI
Agent observability: structured logging, cost tracking, and compliance audit trails
Enables coding agents to coordinate edits, reviews, and escalations without file locking conflicts
MCP proxy server that filters tools from upstream MCP servers via regex-based deny list
Governed MCP orchestration, tamper-evident memory, and Claude Code Seatbelt hooks.
BitTorrent-style mesh for AI inference across agentic CLIs. Local-first.
MCP server fronting a self-hosted coordination-bus HTTP API: post/read/claim/release/heartbeat.
Constitutional-AI safety guardrails for any LLM — personas, constitutions, adjudication.
Statistical checks an agent runs before trusting an AI eval number (is #1 real, judge bias, more).
Real-time LLM output verification with 6-dim contract validation and auto-failover across providers.
Read-only MCP server for AgentLoopKit tasks, policies, reports, handoffs, and status.
A self-improving, verifiable memory layer for AI coding agents.
JMT x402: 35 pay-per-call Base/USDC tools for agents, auto-paid via x402 v2. No API key.
Check whether an AI answer is grounded in its context — deterministic, no LLM judge.
Search the CuratedMCP catalog of risk-classified MCP servers and check verification status.
dev953 method companion: exposes its multi-agent coding method as callable MCP tools.
MCP server for Langfuse LLM observability — trace and observation analysis.
Search and discover MCP servers from the MCP Registry.
Verifiable cognition: prove a session ledger is tamper-evident; audit & import any agent's logs.