Persistent memory and code intelligence for AI coding agents
Persistent memory and code intelligence for AI coding agents
PostgreSQL + pgvector store for @vivantel/rag-core
Zero-dependency TypeScript middleware for dynamic vector space transformation. Warp embeddings at runtime with WASM-accelerated affine transforms, quantization, online learning, and ColBERT — no retraining needed.
The open-source company brain that powers a closed loop — model-free, over MCP. Your AI tool (Claude, Cursor, Copilot) answers from your docs with citations or refuses; record how-work-gets-done as skills, govern real actions with human approval + an audi
Multi-source knowledge plugin for OpenClaw — pgvector + LightRAG injection with optional Jina-powered router & reranker, via before_prompt_build hook
HorizonDB-backed enhanced facts and graph providers for PilotSwarm.
Orchestrateur universel agents IA multi-modeles via MCP. Inclut le protocole 'Custom-Nickname' pour identifier vos agents avec des surnoms originaux (The Chaos Prophet, Shadow Sniper, etc.), l'isolation mémoire (Private Memory Context) et le support pour
Virtual filesystem for AI agents backed by PostgreSQL — ChromaFs-equivalent using just-bash
21 production-grade microservice building blocks for AI-native SaaS — auth, billing, LLM gateway, agent registry, RAG, guardrails, tracing, and more. Each with PostgreSQL, HTTP API, MCP server, and CLI.
Smart, self-maintaining, cross-machine memory for Claude Code — Postgres-backed, no rented LLM brain.
NotNessie core: types, Postgres storage, redaction, embeddings, hybrid search, and context packs.
Local-first MCP context broker for agentic AI knowledge matching and reflection memory.
AskDB RAG layer: deterministic chunker over Schema v2, BYO embedder + vector store (in-memory, file-backed, pgvector), and an optional retriever wired into @askdb/core ask().
pgvector adapter for Eidentic — vector search over PostgreSQL (pg / pglite) using the pgvector extension.
MCP memory server for multi-agent systems, powered by Postgres, pgvector, and Hugging Face.
Config-as-code DSL for commerce search and entity resolution. Declare collection() and entity() with compile-time validation; @samesake/server runs hybrid search and multi-channel matching on PostgreSQL + pgvector.
Official TypeScript SDK for Stackbone — the marketplace and managed runtime for containerized AI agents.