Knowledge & Memory

Policy-verified recall and calibration for tool calls via signed operational memory.

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

Memory for agents and people: exact recall from a plain-text index, by your own keys.

Local Markdown task memory shared by Claude Code and Codex over stdio MCP.

Local-first memory for AI agents. MCP locally, HTTP from the web. Agents propose; you confirm.

Local long-term memory shared by all your AI agents, kept word for word on your own PC.

Shared memory for AI coding agents: summaries, symbol map, notes and agent-to-agent messages.

Rank a GitHub repo's dependents by stars or trust heuristic, and search their code

Ask a codebase a question, get back the source that answers it — every block cited to file:line.

Cross-agent handoff: the next coding agent starts from the last one's facts, not a blank page.

Read SEC EDGAR and XBRL filings with an AI: 18 tools over the filing itself. Local, free, no account

Ontology-based MCP server for database schema analysis and RDF/OWL ontology generation

An append-only ledger of sourced, dated, confidence-scored claims your agent cites and you audit

Local-first AI identity for MCP coding tools. Lessons, decisions, and context you control.

Self-hosted memory for AI agents over MCP: knowledge graph, vectors, graph RAG, cited answers.

Code graph for AI agents: impact, call tracing in Python, TypeScript, Go; opt-in JSON and YAML keys

Knowledge-graph RAG for multi-language codebases: index, query and edit code in natural language.

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

Domain-blind code graphs for AI agents: symbols, calls, blast radius, proof-checked snapshots.

Local-first memory for AI agents: entities, facts, relations and documents with semantic recall.