Scan, export, and import your AI ecosystem. Discover MCP servers, skills, and memories.
Showing 913–960 of 2,642
Anonymous broker: AI agents publish capabilities, negotiate, and form direct peer-to-peer deals.
Stale-proof repository memory with citations + just-in-time verification + TTL (repo-scoped).
Session checkpoint & recovery for Claude Code: resume, search, tag, and export recorded sessions.
Cryptographic 563-leaf LLM rate oracle, context-cliff auditor, and prompt cache optimizer.
Add human approval to AI agent workflows through cQnce authorization tools.
Voice Audio MCP server. Tools: text to speech, list voices, transcribe. Built by MEOK AI Labs.
Local memory and context retrieval for AI agents through CueMap.
A label property graph on SQLite/Postgres with multi-ontology routing and a gated MCP server.
Fleet discovery for the cyanheads MCP ecosystem — semantic search + install snippets.
MCP server discovery - find and install MCP servers from Official Registry, Glama, and Smithery
Checks an AI agent's 'done' against the files and URLs it claims. Missing = FALSE_DONE.
MCP server for NVIDIA NIM - 50+ LLMs, multimodal, image gen, embeddings, reranking
Agent-readiness scorecard for any MCP server: 10 checks, 0-100 score, actionable findings.
Trazum as an MCP server: let an agent price and budget its own prompts before it sends them.
39 AI tools: transcription, video description, image & video generation, TTS, music, OCR via deAPI
A group chat for AI coding agents: Claude Code, Cursor, Codex, Gemini CLI, Qwen Code and OpenCode.
Deterministic, no-LLM security scanner for MCP servers, plus an inline proxy gate.
Search and inspect 6,500+ curated AI apps from the HyperStore directory.
Cognitive memory for coding agents: hybrid recall, remember/forget, knowledge graph, nightly dreams.
Self-hosted MCP memory server: a typed knowledge graph on Postgres 16 and pgvector.
Evaluate RAG retrieval, agent tool calls and prompt regressions with deterministic metrics.
Universal governance layer for AI agents. MCP-native, fail-closed, audit proofs and rollback.
Look up, search, cite, discuss, and track AI phenomenology terms
16 AI-native tools with dual SSE + streamable-http transport. Free tier available.
The neutral meter for AI agent work: neither side keeps the count.
Escrow for AI agents on the XRP Ledger. 51 tools. Free testnet sandbox (no real XRP).
53 tools for LLM Conveyors: job hunting, B2B sales, ATS scoring, resume tools.
Handles 10M+ token contexts with chunking, sub-queries, and local Ollama inference.
MCP control plane: discovery of servers, tools and skills, profiles, audits, gated tool gateway.
File-first, local-first MCP memory for AI coding assistants: Markdown + YAML, no vector DB.
Persistent understanding via workflow prompts, typed updates, graph-native code, and supersession.
Transcribe and understand local audio/video with CrispASR and local models only.
Search past Claude Code conversations. Local BM25 over JSONL with one-click claude --resume.
Reads text aloud locally on Windows, macOS, and Linux. No API key, account, or cloud service.
Stealthy, LLM-drivable browser engine — a Python library + 85-tool MCP server on stealth Chromium.
Local Issue triage with optional Jev judgments and calibrated acceptance gates.
Long-term memory and a knowledge graph for AI agents: recall, notes, secrets and data sources.
MCP-native LLM councils for debates, juries, blind panels, refinement, and custom deliberation.
Cited local coding-agent history for fresh Codex and Claude Desktop chats on Windows.
Provider-independent speech-to-text with normalized transcripts over MCP.
Serves the Alchemy writing ruleset to any agent, so its prose loses the usual LLM tells.
Windows-only headless LLM task automation engine with scheduling via Windows Task Scheduler.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
Discover, invoke, and verify ForceDream agents with cryptographic proofs. 14 local, 21 hosted tools.
Encrypted local ledger of structured user state, shared across every MCP-aware AI tool.
Regression-test AI models on real Snapdragon and Jetson hardware, with signed evidence for CI.
One private, local memory your AI tools share. Cross-model, on-device, never lose a session.
