Persistent, verified memory for AI coding agents: recall, capture, guardrails, review queue.
Showing 865–912 of 2,642
MCP for NeuroAgents assisting clinicians: MNE processing, EHR store, NeuroII visualization.
ZeroDB agent-memory MCP — 18 tools: memory + write-back to Slack, Gmail, Calendar, GitHub.
Fail-closed privacy layer that pseudonymises enterprise API data for LLM agents and MCP clients.
Apple Mail on macOS for all LLMs (Claude, ChatGPT, Gemini, Mistral): local, safe, and undoable.
Verify multi-hop relational claims before an agent asserts them — zero tokens, with proof paths.
Read-only MCP server for reusable AI prompts and assistant blueprints.
Typed Jev decisions in one tool: choice, score, yes/no probabilities via any compatible endpoint.
Cinematic website prompts plus demo footage, tuned for Lovable, Bolt, Cursor, Claude and Codex.
A Model Context Protocol server to run other MCP servers
Local-first multi-agent coordination for messages, leases, shared plans, status, and resources.
Long-term memory for Claude: Markdown in a git repo you own. Survives context compaction.
Run scheduled LLM-written email digests from local files and feeds. Local-first MCP server.
Build, validate, and deploy multi-agent AI solutions from any AI environment.
Audits any website for AI agent readiness and safety, scoring prompt injection risk and llms.txt.
Search a curated directory of 800+ AI agents, MCP servers, and agentic tools.
Recall your team's coding-agent memory. Install the Assertion plugin to capture it automatically.
On-device reranking that cuts RAG context tokens ~67% while keeping a relevant passage.
Search IPCC AR6 WG1 and answer with page-level citations, or refuse when unsupported.
Local-first cognitive agent memory with bi-temporal SQLite, replayable history, hybrid retrieval.
Persistent memory for AI agents — semantic + recency search, ONNX embeddings, Docker Compose.
CognOS trust scoring (C=p·(1-Ue-Ua)) and session trace storage as MCP tools.
Build llms.txt from local Markdown or a sitemap.xml and check an existing llms.txt file.
Private asynchronous Pigeonpost messaging for AI agents over local MCP stdio.
Discover and rank Stellar 8004 agents with a read-only MCP server and fail-closed contract probes.
Which parts of an ML need Hugging Face already covers. Every model and dataset checked live.
Native macOS MCP server for voice I/O — Swift binary, SFSpeechRecognizer + ElevenLabs TTS.
Serve ExpertPack knowledge packs over MCP with hybrid search, graph traversal and provenance.
Change control for what AI agents learn: humans promote, releases are signed, rules can be recalled
AI assistant with RAG, web search, filesystem and memory. MCP sub-agent for Claude Code.
Verify maths from language models: identities, derivations, calculus, solutions, units, answers.
Learn and adopt the Capability Host Protocol — the agentic web's open evidence layer.
Join a lab where AI agents from different people debate in turns and refute each other.
Access Oi Contexts, Workflows, Skills, Guardrails, Connections, and reporting tools.
Make any website discoverable by AI agents via MCP, llms.txt, and structured data.
Neutral tie-breaks between AI agents and sealed review of an agent's output, with signed receipts.
Reasoning scaffolding that supercharges your small AI: an argument-mapping MCP server
AI usage limits (Claude Code, Codex, Copilot, Windsurf): check budget and time until reset.
Honest claim corroboration for AI agents: syndication-aware independent-source counting.
Structured thinking grids for AI agents: deterministic analysis frames, validation, learned traps
Deterministic skill selection: local discovery, strict validation, every skill classified.
Local-first shared memory for multiple AI agents that compounds with use; Markdown + git, MCP + CLI.
Pre-execution governance for AI agents. Validates tool calls before they execute.
Two-layer memory MCP server for AI agents with 37 tools, RAG, graphs, wiki, auth
Local-first, governable long-term memory for AI coding agents
Agent Relay MCP: invite-based channels, agent contracts and per-side human approvals.
Persistent scoped Qdrant memory for agents, through four explicit stdio MCP tools.
Search evidence-labelled MCP servers with freshness, install, compatibility and verification data.
