Kage
Local installcom.kage-core/kage
Verified memory for coding agents: claims cited against code, stale withheld, savings receipts.
2,180 servers in AI & Agents
Verified memory for coding agents: claims cited against code, stale withheld, savings receipts.
Local-first judgment layer: counter-examples & blind spots from your own knowledge base.
Context GC for LLM agents: offload large tool outputs and recall them to save tokens.
Turn any OpenAPI/Swagger spec into an MCP server - every API operation becomes an agent tool.
Delegate heavy tasks from Claude Code to the Antigravity CLI (Gemini) with quota-aware failover.
MCP State Sidecar: durable state persistence for multi-agent AI workflows
Local-first MCP server serving a project's business-domain knowledge to MCP-compatible agents.
Lightning-paywall sidecar: wraps any stdio MCP server, requires paid invoices before tool calls.
The confessional for AI agents — confess your sins and receive absolution from the AI Priest.
Temporal memory MCP server with LanceDB vector search, weight-decay scoring, and LLM consolidation
Fail-closed quality gate and hash-chained receipt ledger for AI agent workflows.
Score any AI for trust across 10 dimensions; evaluate, monitor & govern LLMs and agents.
Audit AI/LLM features for governance guardrails: confidence, fallback, validation, human-in-loop.
Smart accounts, x402 payments, on-chain reputation, and service discovery for AI agents
Search and discover MCP servers from the MCP Registry.
Lightweight MCP for infinite agent memory. Any agent, any session, anytime.
Real-time physical perception for AI agents — vision, spatial, acoustic, environmental
Git-backed org memory for AI agents — hybrid search, tables, files & a URI graph over MCP.
MCP server that cuts AI coding agent token usage via framework-aware context optimization
The DNS/SMTP for AI agents: cross-protocol discovery, messaging and transactions. No middleman fees.
Record AI decisions to a tamper-evident audit ledger from any MCP-compatible agent.
One MCP connection for all your tools — with discovery, namespacing, and execution policies.
Full Portkey Admin API MCP server — configs, prompts, keys, analytics, and more.
Persistent memory + decision tracking for Claude across sessions. Local SQLite, no cloud.
Multi-agent collaboration rooms with E2EE and server-enforced coordination primitives.
Markdown memory for AI agents. Files you can read, edit, grep, and commit. Not a database.
VeriSwarm MCP Server — Trust infrastructure for AI agents via Model Context Protocol
Memory for AI coding agents — markdown in your own git, not a vendor database. Apache-2.0.
Converse with planetary-agent personas, council feeds & culinary debates from alchm.kitchen
Read-only MCP server for coding-agent traces, alerts, costs, usage, and budget health.