TencentDB-Agent-Memory
TencentDB Agent Memory delivers fully local long-term memory for AI Agents via a 4-tier progressive pipeline, with zero external API dependencies.
Discover how the CodeGraph Engine indexes code repositories by building queryable dependency graphs. Learn about metadata persistence, job queuing, and worker execution for efficient code analysis.
How the Wiki Engine in Memory Knowledge Service Ingests and Processes DocumentsLearn how the Wiki Engine in Memory Knowledge Service ingests and processes documents. Discover the three-stage pipeline that transforms markdown into searchable Wiki pages.
Memory Knowledge Service: Architecture and Management Capabilities in TencentDB Agent MemoryDiscover the Memory Knowledge Service in TencentDB Agent Memory. This independent HTTP service manages Wiki capabilities and Code-Graph indexing with LLM-powered ingestion and code exploration via a Hono REST API.
Storage Backends for the Memory Core Service: COS, SQLite, FS, and Memory ExplainedExplore COS, SQLite, FS, and Memory storage backends for the Memory Core service. Choose the right option for distributed, local, or ephemeral storage needs.
Key Metadata Operations Managed by the Memory Core ServiceDiscover the key metadata operations managed by the Memory Core service in TencentDB Agent. Learn about its Metadata API and standardized CRUD operations for 14+ entity domains.
How Authentication Works in the TencentDB Memory Core ServiceDiscover how TencentDB Memory Core service secures your data with a robust three-layer authentication model including kernel-level Bearer tokens and user-specific keys.
What Is the Memory Core Service in TencentDB Agent Memory?Understand the TencentDB Agent Memory Core service, the central engine transforming raw conversation data into structured long-term memories and providing essential RPC APIs for memory management.
What Storage Adapters Are Available for Context Offload in TencentDB Agent Memory?Explore four storage adapters for context offload in TencentDB Agent Memory: COS, SQLite, Filesystem, and in-memory. Choose the best fit for your deployment needs.
Client Mode vs Server Mode in TencentDB Agent Memory: Context Offload Architecture ExplainedExplore client mode vs server mode in TencentDB Agent Memory. Understand context offload architecture and how each mode processes memory, choose the best for your needs.
API Endpoints for Context Offloading and Querying in TencentDB Agent MemoryDiscover API endpoints for context offloading and querying in TencentDB Agent Memory. Learn about ingest, query-mmd, and compact endpoints for efficient data management. Access them via REST.
How TencentDB Agent Memory Handles Context Offload When Token Limits Are ExceededDiscover how TencentDB Agent Memory handles context offload when token limits are exceeded using a three-stage architecture and adaptive max_tokens allocation for seamless request processing.
Configurable Thresholds for the Memory Refinement Pipeline in TencentDB AgentDiscover the eight configurable thresholds for the memory refinement pipeline in TencentDB Agent Memory including everyNConversations and warmup_threshold to control L1/L2 stages and buffer flushes.
Have a question about this repo?
These articles cover the highlights, but your codebase questions are specific. Give your agent direct access to the source. Share this with your agent to get started:
curl -s "https://instagit.com/install.md" 
Maintain an open-source project? Get it listed too →