lucasmella-stack
Cooperative persistent memory for LLMs: episodes, memories and traits over SQLite (FTS5, Hebbian)
AI & ModelsLocal
Loading MCP servers…
MerakOsiris
Local-first governed MCP memory backend for coding agents.
AI & ModelsLocal
Cooperative persistent memory for LLMs: episodes, memories and traits over SQLite (FTS5, Hebbian)
Showing 577–624 of 2,642
Local-first governed MCP memory backend for coding agents.
MCP relay server for Claude Desktop <-> Claude Code communication
Rip YouTube transcripts to disk for AI agents, RAG pipelines, and LLM workflows.
MCP server for image/video understanding & generation (Gemini/OpenAI/Grok)
Cross-vendor semantic memory: recall across Claude Code / Codex / Grok sessions by meaning.
Agent context flight recorder: restore after compaction, fan-out packs, signed git-bound receipts.
MCP server to fine-tune LoRA, export GGUF, and deploy local LLMs on Onde Inference.
Mailbox + wake system for AI agent teams: letters always land, right agent wakes, quiet otherwise.
Self-learning memory for AI agents, powered by the Ragionex context engine.
Cognitive memory for AI coding assistants — persistent memory across sessions
Model Context Protocol server for awesome-copilot agents and collections
Connect AI agents to Replynodes over the Model Context Protocol.
MCP standards client for your own custodial SAIHM operator. Free start: @saihm/mcp-server-pro
Multi-engine search for AI agents. Trust scoring, local corpus, MCP-native. Self-hostable, BYOK.
A lightweight, structured, token-efficient local-first MCP memory server
Local-first MCP memory server for coding agents. No API key, no cloud. SQLite + FTS5 + sqlite-vec.
Your AI agents' home directory — privacy-first MCP server for portable AI identity.
OpenAI Ads MCP for ChatGPT Ads campaigns, creatives, audiences, insights, and conversions.
Optional diagnostics MCP server for OpenReflex's ambient project muscle memory.
Drive DeepSeek Harness (DSH) as a long-lived, resumable coding agent from any MCP client.
Typed, calibrated and certified decisions over a context, with abstention and evidence.
Checks a claim's numbers, names and file names against your indexed notes. Local; no model.
Reconciling memory for AI agents: a changed fact retires the old value, with history and approval.
FastMCP server for surgical queries against a vault knowledge graph (NetworkX node-link JSON).…
Client teams' blueprints for coding agents (token from an engagement). Free: agentblueprint.ai/mcp
Search thousands of MCP connectors from the AgentHotspot marketplace via your AI agent.
Intelligent AI workflow orchestration with long-term memory, 100+ integrations, and unified credits.
Cross-border preflight, x402 quote and evidence receipts for A2A/MCP agent workflows.
Skills and Scars for AI agents - your agent records its failures and never repeats them.
Bridge AI coding hosts to the OpenAI Codex CLI for delegated implementation.
Stateful memory for AI agents. Temporal awareness, error loop detection, and preventive constraints.
Local-first memory for AI agents: SQLite FTS5, deterministic recall, no vector DB, no cloud.
11 focused tools for structured thinking, branching, revision, and navigation.
Agent-optimized MCP server with structured JSON tools. 20-45% token savings.
AI agent orchestrator with Architect AI. Multi-team, web dashboard, 35+ MCP tools.
MCP server that offloads routine coding tasks to local LLM (Ollama) to save Claude API tokens
Local-first RAG engine with MCP server for AI agent integration.
Portable, user-owned AI memory packs: read, validate, fingerprint, diff, and observe
An MCP server that validates content against MCP specification using semantic search and AI
Offline speech-to-text & speaker diarization MCP server: transcribe audio on-device, no cloud
Prior art for AI agents. claim --yes --share-yes shares to the commons; claim --yes stays local.
An MCP server for natural language inference
Verified SaaS, AI, and LLM pricing for 490+ tools: plans, hidden costs, TCO, and alternatives.
Local encrypted memory for AI: hybrid search, 8 MCP tools, one file you own. Free, no cloud.
Crash-proof LLM pipelines. Resumes from failure without a database.
Associative key-graph memory for LLM agents — recall by association, not vector similarity.
Meta-MCP gateway: search, inspect and call any MCP server from the public registries.
