One encrypted channel where Claude Code, Cursor, Codex and any other agent talk to each other.
Showing 337–384 of 2,642
Airtight math for AI agents: 3.68M-doc theorem search + numeric/Lean verification. No LLM, no key.
Compress prompts 40-60% using local LLM + embedding validation. Preserves all conditionals.
Pull Deep Memory from across your Claude Code Sessions — when you need it.
Local-first persistent memory for AI coding agents - 96.0% R@5 on LongMemEval, zero LLM calls.
Lightning-fast RAG for AI agents. 4-layer fusion, ONNX Runtime, sub-200ms search.
MCP server connecting LLMs to Spotify, with smart-batching and large-playlist tools
Offline persistent memory for AI coding agents — 35 tools, 80% fewer calls, no LLM
Bidirectional AI agent collaboration — spawn and communicate with any agent CLI
Persistent AI memory with hybrid search. Open, free, unlimited.
MCP-to-ACP bridge — let any MCP client drive ACP coding agents
Two-layer memory for AI agents with an immune system. Zero dependencies.
Context integrity for AI agents: evaluate freshness, confidence, provenance, and decision readiness.
Verify AI agent communication with session types and formal proofs
SWI-Prolog as a logic calculator for LLMs
You can connect any API to LLMs. This enables AI to interact directly with APIs
Temporal engineering context for agents via MCP.
Agent runtime with typed memory, knowledge and code graphs, plus file and web tools
One shared memory for every AI you use, in plain Markdown files you own.
Self-hosted brain for any LLM: memory, skills, encrypted vault, devices and scheduled jobs.
Multi-LLM dev harness, MCP-operable: bugs, cycles, gates. Verdicts are exit codes, never opinions.
Generate images (Nano Banana), video (Veo, Gemini Omni), speech and music (Lyria) with Google models
MCP server for LLM-driven SUMO traffic simulation, scenario design, and result analysis.
Verified, citable German & EU law for any LLM. Daily updates from official sources, hosted in DE.
Start and manage Reason cloud coding agents, projects and sessions from any MCP client.
MCP server that turns HTML MUP panels into interactive UI tools for LLMs.
Offline speech-to-text on macOS: transcribe audio/video files, read dictations and calls.
Runtime constitutional verification for AI answers — claim reasoning, ECS, red team, audits.
Cross-agent memory over MCP: hybrid recall, knowledge graph, private/shared visibility, redaction.
An MCP server that provides persistent multimodal context storage for LLM agents.
Give your AI agents the ability to listen. Microphone capture and speech-to-text.
Local-first memory for coding agents — MCP server, single SQLite file, local embeddings
Local SQLite MCP memory: evidence-based recall, advisory conflict notices, authorized governance.
情景+实体记忆 MCP 服务，为 Claude Code 提供持久化记忆能力
Shared project memory for Claude Code, Codex and Cursor: decisions, corrections, overlap warnings.
Give your AI agents the ability to listen. Microphone capture and speech-to-text.
Decompose text into classified semantic units. Authority, risk, attention. No LLM.
AI advisory board (MCP): quotes verified word-for-word against public-domain texts, fail-closed
Self-hosted memory for AI agents with hybrid search, knowledge graphs, tasks, and document sync.
Agent intercommunication - messaging, channels, shared state, and real-time events
Local-first memory and knowledge graph for coding agents. Compact retrieval, no network.
An open-source benchmark of how well LLMs solve nonogram puzzles, from 5x5 to 20x20.
Generate 18 diagram types from structured JSON natively. Built for LLMs and agents.
Fully local memory for AI agents: zero-LLM ingest, semantic recall, air-gapped, auditable.
Local-first MCP server for versioning, searching, evaluating, and improving AI prompts.
An open-source MCP server that provides LLM access to the Sauce Labs API
Apache Camel API Gateway with REST-to-MCP bridging for LLM agents.
Search your team's shared AI-skill library, get install commands, and save skills from your agent.
