AI and memory

Self-hosted web search for LLM agents: search -> fetch -> rank pipeline with semantic caching

Portable AI memory as MCP tools: five reads and three controlled writes.

MCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost.

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

Strategic memory agents can build, score and keep current: a living X-Matrix with review cadences.

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

Spec-driven dev workflow MCP: start_* orchestration, memory, GitNexus, quality gates.

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

MCP server that wraps the Qdrant vector database API as tools.

Memory your agent can trust — every answer carries its source; when it doesn't know, it says so.

Local-first memory brain for AI coding agents: hooks capture sessions, beliefs injected per prompt.

Independent, reproducible benchmark harness for agent-memory backends.

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

Exact document sections on demand for LLM agents: index in context, search, read, grep, neighbours.

NVIDIA NemoClaw knowledge graph — 55 nodes, F1 0.576 (+269% vs RAG), 11x fewer tokens. MCP-native.

Google Calendar for LLM agents: find, create, update, move, delete events; free/busy; scheduling.

97-domain knowledge graphs for AI agents — 4× F1 of RAG, 11× fewer tokens. MCP-native.

Shared memory for parallel AI coding agents. Local, free, with rooms and file claims.

Persistent memory with contradiction detection, burnout monitoring, and 69 intelligence tools.

Measure a program's CPU energy and LLM tokens, then refactor it cheaper. Measure, never estimate.

What fills your agent's context window before a session starts: skill descriptions, memory files.

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

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

Local-first long-term memory for AI coding agents. Stored on your own machine.