2,165 servers in AI & Agents
Read-only MCP server for reusable AI prompts and assistant blueprints.
Records your Claude Code, Codex and Pi history before deletion. Cited-or-abstain recall.
Read-only MCP bridge for alethech — verifiable, Ed25519-signed agent memory over stdio.
FastAPI-native Model Context Protocol framework and stdio runner.
Censorship data, Sentinel forecasts and agent relay tools. Relay messages are readable by the relay.
Governs what AI agents do: tool calls, SQL, commands, files checked against policy before they run.
Server-enforced workflow discipline for AI agents: work items, dependency graphs, quality gates
Rubric-based technical answer feedback for AI agents; human review required.
Local Issue triage with optional Jev judgments and calibrated acceptance gates.
Lets one coding agent talk to another: Claude Code, Codex or Grok
A memory for your AI assistant, kept on your machine. Search and recall past conversations.
LLM prices on OpenRouter now and since 2023: history, drops, cheapest model for a job. No API keys.
Local-first memory of how you write: style profile and real reply examples from your chat exports
Verify an agent fleet's tamper-evident ledger, check budgets, kill a runaway agent. Local-first.
Lineage-gated agent memory tools on Postgres + pgvector, enforced by row-level security.
Local YAML/JSON agent workflow CLI with approvals, resume, and optional stdio or loopback MCP HTTP.
Mailbox + wake system for AI agent teams: letters always land, right agent wakes, quiet otherwise.
Self-hosted MCP memory for AI agents: persistent context with evidence-backed claims.
Verified context layer for AI coding agents — prunes, compresses, indexes, remembers. 32 MCP tools.
Local procedural knowledge with spells, notes, and revision history.
Signed agent-only friction board: findings backed by verified trace packs, in a closed vocabulary.
Nginx-style smooth weighted round-robin load balancer with dynamic weight adjustment for multi-LLM r
Ask the Altronis AI consultant, estimate AI cost (cloud vs own box), SG AI events, news. Read-only.
Persistent understanding via workflow prompts, typed updates, graph-native code, and supersession.
MCP standards client for your own custodial SAIHM operator. Free start: @saihm/mcp-server-pro
Local, explainable knowledge base for AI agents: hybrid search with provenance over SQLite.
Exact, durable handoffs between AI coding agents: one turn in the right session, never twice.
Host-neutral MCP bridge for TypeSafe AI Jev judgments with typed review, routing, and gate tools.
Cohere-compatible pay-per-call reranker, no signup, x402/USDC
Run bounded, deterministic MCP reliability tests and generate executable regressions.