dreamd

The plain files in your repo are the memory. dreamd is the local server that reads and writes them.

Drop a .agent/ folder in the project. Claude Code, Cursor, Cline, and other MCP-aware harnesses share it. What one agent learns, the next already knows. You can cat, grep, and git diff every byte. Durable appends go through MCP / the daemon so the writer stays single-writer.

This is not "another memory product." It is a storage-model wedge: the filesystem is the source of truth, and the MCP tools (search_nodes / append_node) are a thin interface over those files.

Open core: Apache-2.0 core today, self-hosted only. Premium features may ship later. Do not read this as free-forever for everything.

npx -y dreamd-mcp setup   # scaffold .agent/ and wire your harness
npx -y dreamd-mcp         # MCP server (stdio) — what the harness spawns

First run prints a local-only privacy disclosure. setup prompts for harness choice when it has a TTY.

The moment it earns its name

~/project $ npx -y dreamd-mcp setup

# Claude Code, Tuesday:
you   > axum keeps blowing up when I unwrap in route handlers
claude> filed under rust::error_handling::axum_rejection

# Cursor, Friday, fresh session:
you   > why is this build failing?
cursor> You're unwrapping in a route handler. dreamd has a
        lesson from Tuesday: axum needs IntoResponse on
        custom Error types. Try `?` and a typed error.

No re-explaining. No re-pasting. Same .agent/ folder, every harness.

Install

npm (recommended)

npx -y dreamd-mcp setup   # scaffold .agent/ + write the harness MCP config
npx -y dreamd-mcp         # MCP server (stdio) — your harness spawns this

Requires a project root sentinel (.git/, Cargo.toml, package.json, or pyproject.toml).

setup prompts when it has a TTY. In scripts and non-interactive shells, pass --yes --harness claude|cursor|both (--harness none or --no-write-mcp scaffolds without touching any MCP config).

Cargo / from source

git clone https://github.com/botzrDev/dreamd.git
cd dreamd
cargo install --path crates/dreamd-cli

See CONTRIBUTING.md for the full dev setup.

Quick start (< 30 seconds)

If ~/your-project is a brand-new folder, run git init first (or make sure it contains one of the supported root sentinels).

cd ~/your-project
npx -y dreamd-mcp setup

# Optional: shared daemon (recommended when several agents write)
npx -y dreamd-mcp watch

Reload your harness. setup already wired the dreamd MCP server, so the harness spawns npx -y dreamd-mcp itself — no config to copy by hand.

Ask the agent to search memory for something you just learned. It calls search_nodes and recalls prior context.

cat .agent/episodic/AGENT_LEARNINGS.jsonl
npx -y dreamd-mcp doctor

The npm shim does not put dreamd on PATH. Use npx -y dreamd-mcp <cmd> on the npm path, or cargo install --path crates/dreamd-cli if you want the dreamd binary.

Adapters: Claude Code · Cursor

What dreamd writes

npx -y dreamd-mcp setup (or dreamd setup after a cargo install) scaffolds the store by calling init, then writes the harness MCP config. init is the scaffold primitive and still works on its own when you want the store without touching any MCP config. Both are idempotent. To uninstall from a machine — stop local servers, remove the socket, unregister the current project, clear caches — run npx -y dreamd-mcp uninstall (project .agent/ stores are left in place). Advanced, registry-only: npx -y dreamd-mcp init --uninstall-project unregisters the current project and touches nothing else.

Architecture (one paragraph)

Agents talk to dreamd over MCP (search_nodes, append_node). The MCP server proxies to a single-writer daemon (dreamd watch) over HTTP on a Unix domain socket, or runs in-process when no daemon is present. The coordinator appends to AGENT_LEARNINGS.jsonl and feeds a Tantivy BM25 index. Recall ranks hits with a query-time salience formula (BM25 × age decay × pain × importance × recurrence). Each hit carries source_harness and skill_action, so recall is attributable across harnesses. The dream cycle consolidates episodic learnings into LESSONS.md under WAL protection.

v0.1 recall is deliberately lexical (BM25 + salience). That is a scope choice, not a scoreboard claim. Semantic / embedding recall is out of scope until after v0.1.

Details: ARCHITECTURE.md · SPEC.md · docs/http-api.md

FAQ

Is this the first / only cross-harness memory? No. Other projects exist (including large ones). dreamd owns the storage-model wedge: plain files you already version-control, not a category claim.

Do I need Rust? No for the recommended path. npx -y dreamd-mcp downloads a prebuilt binary. Rust is only required if you build from source.

Where does memory live? In <project>/.agent/. The daemon and index under .agent/.dreamd/ are local and gitignored. You can read and edit the JSONL / Markdown by hand; durable appends should go through the daemon / MCP so the writer stays single-writer.

What if I want a full wipe? See Full fresh store. There is no dreamd reset --all. To uninstall dreamd itself, run dreamd uninstall — details: packages/dreamd-mcp/README.md.

Windows? Not in v0.1. Linux and macOS only. Windows lifecycle is planned for v0.1.1.

Is everything free forever? Apache-2.0 core is open. Premium may come later. Self-hosted only in v0.1 (no hosted SaaS).

More troubleshooting: docs/troubleshooting.md.

Roadmap

v0.1.1 features are intentionally not implemented or documented as shipped in v0.1 code.

Documentation

Warm recall latency numbers (local Criterion benches) live in PERF.md if you want them. They are not the product pitch.

Status

v0.1.0 is out. npm package dreamd-mcp has held the latest dist-tag since 2026-08-06. CLI commands: setup, init, watch, mcp, dream, doctor, status, recall, score, archive, migrate, reset workspace, uninstall, update, version (dreamd --help is the full list; on the npm path use npx -y dreamd-mcp <cmd> — the shim forwards a subset, see packages/dreamd-mcp/README.md). Linux and macOS.

WasTrue benchmark (Oct 2026)

A separate, reproducible eval measuring whether memory systems correctly update superseded facts. dreamd is one row in the table, published regardless of placement. Conflict of interest is disclosed; configs use each maintainer's documented defaults; raw outputs are committed for audit. Methodology: scripts/benchmark/README.md.

Platforms

v0.1: Linux and macOS. Windows in v0.1.1.

Contributing

See CONTRIBUTING.md. By participating you agree to the Code of Conduct. Security reports: SECURITY.md (do not open a public issue for vulnerabilities).

License

Apache-2.0. See LICENSE and NOTICE.