Skip to content
Back to search

quietmem

Local, precision-first memory for AI coding agents: recalls past conversations only when it is confident they matter. Claude Code hooks + MCP server, pgvector + Ollama, no API keys.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/ronto1138--quietmem/badge.svg)](/listings/ronto1138--quietmem)

HTML

<a href="/listings/ronto1138--quietmem"><img src="/api/listings/ronto1138--quietmem/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Requirements: Node 20+, Docker (or any Postgres 15+ with pgvector), and [Ollama](https://ollama.com).

git clone https://github.com/ronto1138/quietmem && cd quietmem && npm install
ollama pull nomic-embed-text:v1.5

export QUIETMEM_DB_PASSWORD="$(openssl rand -hex 16)"
docker compose up -d

mkdir -p ~/.quietmem && cp quietmem.config.example.json ~/.quietmem/config.json   # edit it: entities, sources
export QUIETMEM_DATABASE_URL="postgresql://quietmem:${QUIETMEM_DB_PASSWORD}@localhost:5433/quietmem"

node bin/quietmem.js init            # tables and indexes
node bin/quietmem.js index --sweep   # index your existing Claude Code transcripts
node bin/quietmem.js tf              # term frequencies used by the precision filters
node bin/quietmem.js doctor          # checks everything and times each phase

Keep `QUIETMEM_DATABASE_URL` in your shell profile (not in the config file), so the password never lands in a file you might share.

Claude Code

node bin/quietmem.js install claude-code          # prints the hooks to add to ~/.claude/settings.json
node bin/quietmem.js install claude-code --write  # or merges them for you (keeps a backup)

That adds two hooks: `UserPromptSubmit` runs recall, and `Stop` indexes what was just said, in the background.

Any MCP client

{ "mcpServers": { "quietmem": { "command": "node", "args": ["/path/to/quietmem/bin/quietmem.js", "mcp"],
  "env": { "QUIETMEM_DATABASE_URL": "postgresql://quietmem:...@localhost:5433/quietmem" } } } }

Tools: `search_memory` (plain search the model can call when the user refers to earlier work) and `recall_memory` (the same gated recall the hooks use). Clients without hooks cannot inject automatically, so indexing their conversations needs an adapter or an export to the [JSONL format](docs/adapters.md).

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 102 lines
  1. # quietmem
  2. **Local, precision-first memory for AI coding agents.** quietmem indexes your past conversations with your
  3. agents and, when a new message clearly relates to something you discussed before, quietly hands the
  4. relevant fragments to the model. When it is not confident, it injects nothing.
  5. - **Everything local.** Postgres + pgvector and a local embedding model (Ollama by default). No API keys
  6. needed, no cloud, no telemetry.
  7. - **No resident process.** Hooks start, do their work and exit. Recall has a hard time budget (500 ms by
  8. default): if it cannot answer in time, the message goes through untouched.
  9. - **Precision over recall.** Similarity alone is a bad signal: "yes, go ahead" scores 0.74 against half
  10. your history. quietmem requires the message to name something known (a project, a client, a tool) or to
  11. ask to remember, and every fragment must share distinctive terms with it. See [docs/design.md](docs/design.md).
  12. - **Secrets stay masked.** Transcripts contain pasted keys. Everything quietmem prints goes through a redactor.
  13. - **Memory you approve.** An optional nightly job reads the day's conversations and *proposes* durable
  14. memories (decisions, preferences, references) as Markdown files. Nothing is written until you accept it.
  15. - **Any harness, any model.** Hooks for Claude Code; an MCP server for Cursor, Codex CLI, Windsurf, Zed,
  16. Claude Desktop and any other MCP client; a plain JSONL format for everything else. Embeddings from
  17. Ollama or any OpenAI-compatible endpoint; proposals from whatever command you configure (`claude -p`,
  18. `codex exec`, `ollama run`, your own script).
  19. ## Why
  20. quietmem started as a replacement for a third-party memory plugin that injected too much, ran a resident
  21. server, and quietly spent a lot of API tokens. The goal was the opposite on every axis: local, silent when
  22. unsure, measurable, and free to run. It has been in daily use across a dozen projects since September 2026,
  23. on a corpus of 50k+ chunks in Spanish and English.
  24. ## Quick start
  25. Requirements: Node 20+, Docker (or any Postgres 15+ with pgvector), and [Ollama](https://ollama.com).
  26. ```bash
  27. git clone https://github.com/ronto1138/quietmem && cd quietmem && npm install
  28. ollama pull nomic-embed-text:v1.5
  29. export QUIETMEM_DB_PASSWORD="$(openssl rand -hex 16)"
  30. docker compose up -d
  31. mkdir -p ~/.quietmem && cp quietmem.config.example.json ~/.quietmem/config.json # edit it: entities, sources
  32. export QUIETMEM_DATABASE_URL="postgresql://quietmem:${QUIETMEM_DB_PASSWORD}@localhost:5433/quietmem"
  33. node bin/quietmem.js init # tables and indexes
  34. node bin/quietmem.js index --sweep # index your existing Claude Code transcripts
  35. node bin/quietmem.js tf # term frequencies used by the precision filters
  36. node bin/quietmem.js doctor # checks everything and times each phase
  37. ```
  38. Keep `QUIETMEM_DATABASE_URL` in your shell profile (not in the config file), so the password never lands in a
  39. file you might share.
  40. ### Claude Code
  41. ```bash
  42. node bin/quietmem.js install claude-code # prints the hooks to add to ~/.claude/settings.json
  43. node bin/quietmem.js install claude-code --write # or merges them for you (keeps a backup)
  44. ```
  45. That adds two hooks: `UserPromptSubmit` runs recall, and `Stop` indexes what was just said, in the background.
  46. ### Any MCP client
  47. ```json
  48. { "mcpServers": { "quietmem": { "command": "node", "args": ["/path/to/quietmem/bin/quietmem.js", "mcp"],
  49. "env": { "QUIETMEM_DATABASE_URL": "postgresql://quietmem:...@localhost:5433/quietmem" } } } }
  50. ```
  51. Tools: `search_memory` (plain search the model can call when the user refers to earlier work) and
  52. `recall_memory` (the same gated recall the hooks use). Clients without hooks cannot inject automatically,
  53. so indexing their conversations needs an adapter or an export to the [JSONL format](docs/adapters.md).
  54. ## Commands
  55. | Command | What it does |
  56. |---|---|
  57. | `quietmem init` | Create tables and indexes (dimensions and index type from the config) |
  58. | `quietmem doctor` | Check config, embedder and database; time a cold and a warm vector query |
  59. | `quietmem index --sweep` | Index everything new in the configured sources |
  60. | `quietmem index <file> [--adapter jsonl]` | Index one transcript |
  61. | `quietmem tf` | Rebuild term frequencies (after big corpus changes) |
  62. | `quietmem recall "text" [--debug]` | See what the gates would do with a message |
  63. | `quietmem search "text" [--project p]` | Plain semantic search, no gates |
  64. | `quietmem mcp` | MCP server over stdio |
  65. | `quietmem distill [--date d] [--project p]` | Propose memories from a day of conversation |
  66. | `quietmem proposals expire` | Move stale pending proposals to `expired/` |
  67. ## Documentation
  68. - [Configuration](docs/configuration.md): every option, entities, project labels, embedders
  69. - [Design](docs/design.md): the gates, why they exist, how to tune them on your corpus
  70. - [Adapters](docs/adapters.md): add support for another harness (the best first contribution)
  71. - [Performance](docs/performance.md): the recall budget and keeping the index warm
  72. ## Status
  73. v0.1. Used daily by its author; the generalized packaging is new. Expect rough edges, and please open
  74. issues. Contributions are very welcome, especially adapters for other harnesses and calibration results
  75. on corpora in other languages: see [CONTRIBUTING.md](CONTRIBUTING.md).
  76. ## License
  77. [MIT](LICENSE)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.