Why it matters
Profile
Anticipatory memory for AI agents with RAG and vector search. Pre-fetches relevant context before queries hit the agent.
setup mediumintegration mediuminterface cli
Provenance
Signals
Listed in the awesome-hermes-agent README
Sources: 2 / Surfaces: 1
Fast skim
What the upstream surface says
Short excerpt only, so you can decide whether to click out.
The fastest, most trustworthy memory layer for coding agents.
FlowState-QMD turns local markdown knowledge into shared project memory for Codex-, Claude-, Cursor-, and MCP-style agents. It combines a durable markdown memory store with a FlowState anticipatory cache so agents can pull relevant context before they fall into a reactive search loop.
[](https://opensource.org/licenses/MIT) [](https://github.com/tobi/qmd) [](#)
FlowState-QMDWhy This WinsMemory Model90-Second QuickstartVerify the host, recommend a profile, and emit wrapper configsInspect readiness any timeIndex your repo memoryStart the coding-agent memory server
- Built for coding agents. It works best on docs, ADRs, RFCs, notes, runbooks, changelogs, migration logs, and benchmark writeups.
- Local-first and inspectable. Everything runs on your machine with SQLite, sqlite-vec, and local GGUF models via node-llama-cpp.
- MCP-native. The default experience is a clean MCP server plus a packaged agent skill.
- Trust over magic. Results keep file paths, doc IDs, snippets, and explain traces so the agent can show its work.
- Durable knowledge: indexed markdown files in named collections
- Working memory: the FlowState anticipatory cache at ~/.cache/qmd/intuition.json
- Context overlays: human-authored collection/path summaries added with qmd context add
- Index a repo's docs/, notes/, CHANGELOG.md, and ADRs.