Knowledge & Memory

Cognitive memory for AI agents — semantic recall, knowledge graph, and contradiction detection

Persistent local memory for coding agents: temporal knowledge graph, procedural and episodic recall

Corrections that outlive the session. A guard blocks the edit that writes the old value back.

Self-correcting agent memory: recall, supersede, revert, forget, GDPR erasure, audit receipts.

Local-first memory — 100+ tools, 99.2% LongMemEval-S retrieval@10, hybrid search, GDPR, no cloud.

Local-first agent memory over SQLite: remember, recall, link, forget. Degrades, never fails.

Open-source causal memory for AI agents: persistent, explainable, MCP-native memory (13 tools).

Local Markdown/Obsidian knowledge substrate for MCP agents with governed memory and hybrid search.

Local-first, governable long-term memory for AI coding agents

Scoped memory for coding agents: picks the right project, answers in scope, or abstains.

Memory for coding agents, checked against the filesystem and git before it is believed.

Coding agent memory — one local MCP server for every project. Warns before repeating failed fixes.

Git-versioned markdown memory for AI agents: save, search, compact, lint, and audit.

Microsoft Outlook personal accounts: mail, calendar, contacts, to-do, drafts (62 tools).

Hand a project over with the reasons attached. Local-first cross-agent memory MCP + drift detection.

Seeds, governs and navigates a memory_bank knowledge base: gated writes, routing, drift vs code

Local-first agent memory. Source, date, bind/abstain. Permanent name: lbrain.ai/claim.html

Private Agent memory and governed shared knowledge.

Architectural decision memory for LLM-native workflows — markdown for humans, a graph for agents.

Prior art for AI agents. Ask a claim index before retrying a known failure.