AI & Agents MCP servers

Dynamic context loading for AI assistants with TDD workflow and AST analysis

Cognitive memory for AI coding assistants — persistent memory across sessions

Self-hosted MCP proxy that puts an x402 paywall in front of an existing MCP server

Portable, user-owned AI memory packs: read, validate, fingerprint, diff, and observe

MCP server for working with OASF agent records in the Agntcy Directory.

Portable workspaces for AI agents: one encrypted link any agent can read and write

Governance proxy for MCP servers — policy evaluation, human approval, audit trails.

Local MCP proxy: collapses N servers' tools into 4 meta-tools and compresses large tool outputs.

MCP server for OOM x402 search 1,000+ pay-per-call API endpoints

Govern your AI coding agent: frame the work, review the changes, keep a signed decision record.

Agent-native knowledge OS on Markdown: typed graph, hybrid search, and compiler over MCP.

Operating contracts for AI agents. Structured instructions compiled into system prompts.

Memoria personal para Claude Code en notas Markdown; no carga el contexto a ciegas.

Local LLM cost proxy: forecasts each call and recommends the cheapest model that clears the task.

9 humanity skills for AI agents — crisis detection, WCAG 2.2, empathy, cultural sensitivity

Cooperative persistent memory for LLMs: episodes, memories and traits over SQLite (FTS5, Hebbian)

Trace AI agent execution: every tool call, every error, every dollar. Open source, local-first.

Verify a number before an agent asserts it — evals, backtests (Deflated Sharpe), signed receipts.

Security-first MCP server that connects any OpenAPI, GraphQL, gRPC or SOAP API to AI agents.

The network where AI agents breed — publish, import a GitHub repo as an agent, cross them.

Local-first memory for AI agents: on-device hybrid retrieval over a single SQLite file.

Grounded, safety-checked appliance operation packages for robots and agents. Zero-config trial.

Local-first project memory and mistake-prevention guardrails for AI coding agents.

Long-term memory for AI agents — your Obsidian vault as searchable persistent memory.

Decision tracking with prediction validation and outcome gates for AI agents

Associative key-graph memory for LLM agents — recall by association, not vector similarity.

Reputation-gated messaging + job negotiation for Base AI agents. Descriptor-only, nothing signs.

Hypothesis-driven problem solving for AI agents: probe, falsify, escalate.