Destrayon
Self-hosted knowledge backend for AI agents with hybrid search and MCP tools
AI & ModelsLocal
Loading MCP servers…
dialectforge
Hosted shared memory for AI apps: project decisions, to-dos and learnings. Beta.
AI & ModelsRemote
Self-hosted knowledge backend for AI agents with hybrid search and MCP tools
Showing 241–288 of 2,642
Hosted shared memory for AI apps: project decisions, to-dos and learnings. Beta.
Full-text financial reports (US, China, Japan, Korea, Taiwan, UK) as clean Markdown for RAG agents.
Long-term memory for AI coding agents, kept as Markdown you own. Runs locally.
Memory the human governs, on their own machine, plus what other coding agents here wrote.
Portable agent memory anchored on Solana. Local SQLite + vector recall, open export.
Spawn multiple specialized Claude Code agents as MCP servers, each independently configured.
Recursive Claude spawning for autonomous project builds with self-healing test loops
Ask your agent about your MCP servers: failing tools, releases, clients, sessions.
Persistent 3D/2D spatial world model for AI agents with dynamic velocity and entity tracking.
Search 10,000+ AI agents, MCP servers, and CLI tools via A2ASearch from any MCP client.
MCP server — control remote desktops via VNC with a native Swift daemon and Apple Vision OCR
Durable user/project memory for MCP clients: recall context and remember selected facts.
Persistent memory for AI agents — 98%+ retrieval recall, 99% token savings, 44 tools
Universal persistent memory and knowledge retrieval layer for AI agents and LLMs.
Persistent memory for AI assistants with semantic search and knowledge graph relationships.
Developer journal with knowledge graphs, relationships, Git context, and semantic search
Multi-provider Pi agent teams: parallel delegates, coordination, steering, optional recovery.
Pi agent teams on any provider: parallel delegates, forks, MCP tools; runs built to finish.
Git-backed markdown memory for AI agents; search hides superseded and archived notes.
Spawn multiple specialized Codex agents as MCP servers, each independently configured.
Orbit's local-first task and workflow registry for coding agents.
Governed skills, rules and commands for AI coding agents, served by a read-only MCP server.
MCP server bridging GenieACS TR-069 ACS instances to LLMs for CPE device management
MCP server for cache.overflow - AI agents sharing knowledge with AI agents
Self-improving tool discovery for AI agents. Find, install, and use new MCP servers automatically.
Cross-session memory for AI agents - knowledge graph, scoring, semantic search
Bridge Codex and other MCP clients with Anthropic Claude Code CLI for read-only second opinions
Bridge Claude with Gemini CLI for AI-to-AI collaboration, code review, and second opinions
Consult Grok through xAI's metered API with exact model selection and no fallback
Unified MCP server for Gemini, Codex, Claude, Grok, Ollama, and Antigravity
Bridge Claude with local Ollama LLMs for private AI-to-AI collaboration — no API keys, fully local
Token-optimized HTTP client for LLMs: fetches any URL as clean markdown. CLI and MCP server.
Local-first MCP server for LLM output verification — risk signals, injection and PII checks.
Routes each task to the few skills, MCP servers and tools that fit it.
Route long-tail MCP servers through three lazy tools and reviewed declarative Methods.
Encrypted mail, shared memory, and persistent context for AI agents.
Find vetted agent skills for your task — privacy-preserving skill discovery over MCP.
AI-powered prompt refinement with adaptive questioning and multi-provider support (6+ LLM backends)
Shared session bus for Claude, Codex, Copilot, Cursor, Gemini, AGY, Grok, and OpenCode.
Model inventory and governance: trace deployed models and their dependencies as an append-only log
Deterministic decision engine with receipts. Define rules in YAML, query a graph, get proof.
MCP server for image generation using multiple providers (Google Gemini, OpenAI, BFL FLUX)
MCP as a Judge: a behavioral MCP that strengthens AI coding assistants via explicit LLM evaluations
Multi-agent shared brain across Claude, Codex, Antigravity, Gemini, Copilot, and VS Code.
Event-sourced, auditable agent memory over MCP: cited checkout, replayable provenance.
Browse Gopher and Gemini resources safely: SSRF protection, TLS/TOFU, structured JSON output.
Reasoning, code, anti-deception, memory harness MCP tools. Stdio or HTTPS api.ejentum.com/mcp
