Local-first knowledge engine for AI agents: memory, graph, and recall over MCP.
Showing 2,209–2,256 of 35,375
Strategic BDI reasoning engine for autonomous AI agents with spatial utility and replanning.
MCP server for the Rclone RC API, with selectable toolsets.
Sandboxed computer-use for AI agents: drive real browser + desktop apps in nested X11 windows
Read-only Rasmio (rasmio.com): Iranian companies, board members, gazette ads, products, brands.
Local grounded memory for coding agents: MCP over stdio, stdlib only, a verdict per answer
US shopping research with real prices, sellers, and purchase links from Amazon, Best Buy, Walmart.
Observe any running process from your agent. strace, py-spy, perf, lsof, tcpdump as evidence.
Observe any running process from your agent. strace, py-spy, perf, lsof, tcpdump as evidence.
RTL and FPGA tools: lint, simulate, formal, synthesize, place and route, program a board.
AI-agent programming language. JSON AST in, WASM out. Typed, effect-tracked, Z3-verified.
MCP server that loads and serves skills from a mounted directory with hot reload.
MCP server that loads and serves skills from a mounted directory with hot reload.
Vet a package (CVEs, license, maintenance) before your AI agent uses it, plus capability discovery.
40 MCP tools for 11 Indonesian government portals — BPOM, BPJPH, AHU, OJK, BMKG+
MCP-native Trust Infrastructure for AI Agents. Persistent encrypted memory with Trust Quotient.
Zero-Knowledge Context™ & Neural Handover™ for AI Agents. The Trust Layer for AI Memory.
18 deterministic calendar tools: contact resolution, temporal context, availability, booking
Governed Obsidian vault access: hybrid retrieval, Markdown-native memory, HITL confirmations.
Governed Obsidian vault access: hybrid retrieval, Markdown-native memory, HITL confirmations.
MCP server for 1C Enterprise — ERP catalogs, documents via REST API (Russia)
USB-HID keyboard/mouse (Pico 2, open firmware) as MCP tools; --mock runs with no hardware
Local-first TDLib Telegram MCP server with 126 tools, account isolation and production guardrails.
Execute TypeQL queries and manage databases and users on a TypeDB server.
MCP server for Monarch Money — accounts, transactions, budgets, cashflow, investments, and more
Put a game on Steam: store page, achievements, Valve-rule checks, market data, Steamworks.
MCP server for CIPP — M365 multi-tenant management for MSPs (users, tenants, policies).
MCP server for CIPP — M365 multi-tenant management for MSPs (users, tenants, policies).
Local MCP runtime for policy-governed, verified agent actions with durable receipts.
MCP server for managing Caddy web servers via the admin API
Rank CS/AI/ML papers by citations, forecast impact, or code adoption; trace 23.2M citation edges.
Shared, governed long-term memory for AI agents across tools and sessions via MCP and REST.
Search EU legislation, CJEU case law, and treaties; traverse CELLAR graph; browse EuroVoc concepts.
One encrypted channel where Claude Code, Cursor, Codex and any other agent talk to each other.
Pre-install security scans for npm packages, MCP servers, and AI agents with cited verdict evidence.
Bitcoin-native MCP server for AI agents: BTC/STX wallets, DeFi yield, sBTC peg, NFTs, x402 payments.
Inspect, drive and debug a running Ren'Py game: state, screenshots, guarded clicks, saves, builds.
Airtight math for AI agents: 3.68M-doc theorem search + numeric/Lean verification. No LLM, no key.
EU AI Act + GDPR compliance scanner. One call, no arguments, 10 seconds. 22 AI frameworks detected.
The trust and intelligence layer between AI agents and your database.
Write-capable PDF toolkit MCP: 22 tools to read, create, render, encrypt, merge & fill PDFs.
Compress prompts 40-60% using local LLM + embedding validation. Preserves all conditionals.
Security scanner for MCP servers and skill files. Detects AVE vulnerabilities before production.
Security scanner for MCP servers and skill files. Detects AVE vulnerabilities before production.
Pull Deep Memory from across your Claude Code Sessions — when you need it.
Coherence guard for shared files: denies stale writes so agents don't silently overwrite each other.
Secure MCP gateway and quarantine for AI agent traffic — three-layer prompt injection defense
Full Paperless-ngx API for AI assistants: search, tag, edit and upload documents, workflows and more
