Categories
Developer Tools Automation Database Knowledge Management Machine Learning Artificial IntelligenceStars
Forks
Watchers
Developer links
TencentDB Agent Memory
TencentDB Agent Memory provides a team-level memory hub that transforms AI agent conversations, documents, and codebases into four governed, shareable memory assets: Chat Memory for conversation history, Skills extracted from completed tasks, LLM-Wiki built from document ingestion, and Code-Graph generated from codebase analysis. The four-tier semantic pyramid structures long-term memory from L0 raw conversation capture through L1 episodic extraction and L2 scenario aggregation to L3 persona synthesis, enabling hierarchical drill-down via node and result references instead of flat vector recall. The Node.js Gateway sidecar handles capture, extraction, storage, recall, and pipeline scheduling through RESTful HTTP v2 endpoints on port 8420, while the Memory Proxy intercepts Anthropic-format API calls to inject team memory context into Claude Code, CodeBuddy, and other coding agents transparently. Local SQLite with the sqlite-vec extension provides the default storage backend with hybrid BM25 keyword plus vector embedding plus reciprocal rank fusion retrieval requiring zero external API dependencies. Teams manage ownership, versions, status, visibility, usage counts, and agent bindings through the Memory Hub dashboard with role-based access control separating System Admin and team-level Admin and Member permissions. Official TypeScript and Python SDKs provide programmatic access for custom framework integration beyond the built-in OpenClaw plugin and Hermes Agent adapter. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
Benefits
- Four Reusable Memory Assets
- Automatically extracts Chat Memory, Skills, LLM-Wiki, and Code-Graph from conversations, tasks, documents, and codebases into governed team-level assets with version tracking.
- Four-Tier Semantic Pyramid
- Structures memory from L0 conversation capture through L1 episodic extraction and L2 scenario aggregation to L3 persona synthesis with hierarchical drill-down retrieval.
- Zero External API Dependencies
- Runs entirely locally using SQLite with sqlite-vec for hybrid BM25 keyword plus vector embedding retrieval, requiring no external database or cloud API connections.
- Cross-Framework Agent Compatibility
- Memory assets decouple from specific agent frameworks, enabling portability across OpenClaw, Hermes, Claude Code, and CodeBuddy with official TypeScript and Python SDKs.
Features
- Memory Gateway Service
- Node.js sidecar handles capture, extraction, storage, recall, and pipeline scheduling through RESTful HTTP v2 endpoints on port 8420.
- Memory Proxy for Coding Agents
- Intercepts Anthropic-format API calls to transparently inject team L2 and Code-Graph memory context into Claude Code sessions.
- Team Memory Hub Dashboard
- Manage ownership, versions, status, visibility, agent bindings, and role-based access control with System Admin and team-level permission layers.
- Hybrid Retrieval Pipeline
- Combines BM25 keyword search with vector embedding similarity and reciprocal rank fusion for deterministic structured recall across all memory tiers.
- Cold-Start Document Import
- Import existing documents, codebases, and conversation sessions so new agent teams load accumulated experience instead of learning from scratch.