AI and memory

Long-term memory for AI agents — your Obsidian vault as searchable persistent memory.

Hosted AI agent memory that learns from outcomes, with shared rooms, in Claude, Cursor and ChatGPT.

Scan prompts for injection attacks, redact PII, and audit LLM SDK usage from any MCP client

Branchable LLM history DAG + encrypted context capsules agents can save, restore, and crypto-shred.

Memory for coding conventions and standing instructions that persists across sessions.

Local-first shared memory for AI tools. Your files, encrypted at rest by default; budgeted reads.

Geospatial analysis: vector and raster GIS operations, cartographic maps, spatial data access

Let any LLM watch a video locally — and search everything it has ever watched.

Recovers malformed LLM JSON. MCP build: 218/300 on MALFORMED-300 (library build 282/300).

Local-first memory for AI agents: ground truths, failure firewall, negotiated recall over MCP.

Local adaptive memory for AI coding agents through a five-tool MCP lifecycle.

Local multi-channel message emulator for E2E testing, with MCP tools for LLM agents.

Cognitive memory for AI coding assistants — persistent memory across sessions

MCP server for AI image generation via OpenAI, Stable Diffusion (SD WebUI), or placeholders.

Governed, self-hosted memory for AI agents: writes queue until a named person approves.

Deterministic PC no-boot/no-POST diagnostics: real beep-code tables, no LLM guessing.

Self-curating shared memory that keeps your agents working like a high-performing team

Analyze LLM API costs: token waste detection, caching savings estimates, model comparison

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

Self-hosted shared memory for a team of AI agents. Rooms, L0-L3 depth, no LLM on the read path.

On-device, self-organizing memory for AI coding agents — recalls the right facts into each prompt.

Review gate for shared agent memory: an unreviewed or hand-edited memory is never served.

Connect MCP-capable AI agents to local Granoflow tasks, reviews, cards, imports, and work memory.

Local-only MCP server for source-attributed Markdown memory and documentation retrieval.