# remem: Local-first memory for Claude Code and OpenAI Codex

[![MCP Toplist](https://mcptoplist.com/badge/io.github.majiayu000%2Fremem.svg)](https://mcptoplist.com/server/io.github.majiayu000%2Fremem)

> Stop re-explaining your project every new coding-agent session.

Language: **English** | [简体中文](README.zh-CN.md)

`remem` automatically captures, distills, searches, and injects engineering
memory across Claude Code and OpenAI Codex CLI sessions. Decisions,
bug-fix rationale, project patterns, and preferences stay available through
hooks, MCP, CLI, and a localhost REST API.

[![CI](https://github.com/majiayu000/remem/actions/workflows/ci.yml/badge.svg)](https://github.com/majiayu000/remem/actions/workflows/ci.yml)
[![Release](https://img.shields.io/github/v/release/majiayu000/remem?sort=semver)](https://github.com/majiayu000/remem/releases/latest)
[![crates.io](https://img.shields.io/crates/v/remem-ai)](https://crates.io/crates/remem-ai)
[![npm](https://img.shields.io/npm/v/%40remem-ai%2Fremem)](https://www.npmjs.com/package/@remem-ai/remem)
[![License MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)

![Remem recall demo showing a new session picking up an earlier bug fix](assets/remem-recall-demo.gif)

*A new Claude Code session recalls the earlier root cause, commit, and open
TODO with memory citations and no re-explaining.*

## What remem gives you

- Automatic session capture and background LLM distillation.
- Project-scoped recall across Claude Code and Codex using one local store.
- Searchable decisions, bug fixes, architecture notes, preferences, and raw
  session evidence.
- Source attribution, staleness labels, suppression, review queues, and
  injection audits.
- SQLite with SQLCipher encryption by default for fresh installs.
- MCP, CLI, and authenticated localhost REST access from one Rust runtime.

remem prioritizes memory quality. Automatic capture is the primary path;
manual `save_memory` calls supplement it when a decision needs to be recorded
immediately.

## Install in five minutes

### Homebrew

```bash
brew install majiayu000/tap/remem
"$(brew --prefix remem)/bin/remem" install --target codex
```

Use `--target claude` for Claude Code. `--target all` configures every known
host, including Cursor where its v1 renderer is supported.

### Standalone installer

```bash
curl -fsSL https://raw.githubusercontent.com/majiayu000/remem/main/install.sh | env REMEM_NO_CONFIG=1 sh
~/.local/bin/remem install --target codex
```

### npm or Cargo

```bash
npm install -g @remem-ai/remem
# or
cargo install remem-ai --bin remem

remem install --target codex
```

GitHub Releases: prebuilt binaries for macOS and Linux on x64/arm64, with
published checksums. Use one canonical `remem` executable on `PATH`;
`remem doctor` warns when hooks and terminals resolve different copies.

For channel-specific upgrades, platform boundaries, PATH drift, and manual
install notes, read the [installation and upgrade guide](docs/installation.md).
The broader [documentation guide](docs/README.md) links plugin and operational
material.

## Verify the installation

Restart the selected coding agent, then run:

```bash
remem doctor
remem status
remem search "last decision"
```

A healthy Claude Code or Codex installation injects relevant project memory at
SessionStart and queues durable session distillation at Stop. Codex also uses
`UserPromptSubmit` to capture each prompt and surface compact optional memory
candidates. `remem doctor` checks the schema, encryption key, database, hooks,
MCP registration, worker, and common install-path drift.

Repository contributors can verify duplicate SessionStart suppression with the
[isolated executable smoke fixture](scripts/ci/smoke_sessionstart_context_gate.sh).

For a focused, read-only view of current-memory truth:

```bash
remem doctor truth --cwd .
```

## Host support

| Capability | Claude Code | Codex CLI | Cursor v1 |
|---|---|---|---|
| MCP memory tools | Yes | Yes | Yes on macOS/Linux |
| SessionStart injection | Yes | Yes | Not supported |
| Automatic session memory | Yes | Yes, Stop-based and low-noise | Not enabled by the v1 installer |
| Tool-event capture | Installed hooks | No high-frequency Bash hook by default | Runtime command exists; no installed hook |
| Compiled command-rule enforcement | Optional warn/block on Bash | Not supported | Not supported |
| Windows | Supported | Supported | Not supported |

Cursor's v1 installer registers MCP only. The verified `observe` and
`summarize` runtime commands exist, but `remem install --target cursor` does
not install automatic capture hooks or SessionStart injection.

The repository also includes a Codex plugin wrapper. See
[plugins/remem/README.md](plugins/remem/README.md) for local plugin runtime and
explicit hook activation instructions.

## Why use remem alongside built-in memory

Built-in `MEMORY.md`, `CLAUDE.md`, and agent instruction files are ideal for a
small set of stable facts that should always be visible. remem covers the
engineering history that is too large, dynamic, or evidence-heavy to maintain
by hand.

| Need | Built-in files | remem |
|---|---|---|
| Stable project rules | Excellent | Supported |
| Evolving context | Handwritten instructions; Claude Code auto memory also writes notes | Hook-driven session capture and background distillation |
| Search older rationale | Limited by loaded text | Curated and raw search |
| Branch, time, and staleness handling | Manual | Built in |
| Provenance and injection audit | Git history | Database-backed audit |
| Review, suppression, and lifecycle governance | Manual edits | First-class commands |

[Claude Code auto memory](https://code.claude.com/docs/en/memory) already saves
notes automatically. The distinction is the memory surface and its evidence,
retrieval, and lifecycle controls, rather than automatic persistence alone.

Use both. Keep concise rules in native files and let remem retain the long tail
of decisions, failures, evidence, and changing project state.

The broader ecosystem comparison lives in the dated
[memory-tool survey](docs/research/claude-memory-mcp-ecosystem-2026-03.md).

## How it works

```text
Claude Code / Codex hooks
          |
          v
append-only captured_events ledger
          |
          v
coalesced background extraction and session rollup
          |
          v
governed candidates -> curated memories + workstreams + raw archive
          |
          v
FTS, entity, temporal, vector, graph, and optional local rerank retrieval
          |
          v
budgeted, source-attributed SessionStart context
```

Hooks return quickly after durable capture or queueing. Background workers
perform extraction, candidate governance, compression, retrieval enrichment,
and lifecycle cleanup. MCP, CLI, REST, and SessionStart share the same local
store and governance model, but apply surface-specific eligibility policies.
Explicit search is an inspection and recovery surface, so it may return
labeled `legacy_unverified` memories; default SessionStart and CurrentTruth
exclude those rows and record the reason.

Generated memory is treated as untrusted until it passes source-support,
secret, instruction-pattern, scope, and lifecycle checks. Unsafe content is
dropped or routed to review with a diagnosable reason.

For module ownership and current data flow, read
[docs/ARCHITECTURE.md](docs/ARCHITECTURE.md).

The experimental MCP `context_bundle` tool exposes the versioned, budgeted
compiler to explicit callers. The experimental `remem context-plan` command
prints a request-specific retrieval plan. These opt-in interfaces are tracked
by the [Context Bundle](docs/specs/GH932/PRODUCT.md) and
[retrieval-router](docs/specs/GH934/PRODUCT.md) contracts.

The default Codex integration stays low-noise: `SessionStart` provides stable
context, `UserPromptSubmit` provides a compact candidate index, and `Stop`
queues background summarization. Prompt candidates contain IDs, titles,
state, retrieval reason, estimated read cost, and a detail lookup hint, but no
memory bodies. They are optional leads that Codex may ignore, open, or search
beyond. The first prompt may also receive up to two continuity anchors so a
prompt such as `continue` does not depend on lexical overlap. Existing hybrid
RRF ranks memory candidates; no final confidence threshold decides relevance
for the model. Automatic extraction asks for short, specific candidate titles
without a redundant project-name prefix; existing stored titles remain intact.

For your own Codex sidebar, an optional rename convention is
`MMDD｜TYPE｜Topic`, such as `0903｜FIX｜FTS5 tokenizer mismatch`. If you use a
separate host-supported rename workflow, preview its proposed names before
applying a batch. This is host-sidebar organization only: Remem does not rename
host conversations or import those names as intent overrides. Remem's structured
session/workstream fields remain authoritative, and a host title does not change
memory types or workstream identity. See the
[session intent contract](docs/specs/session-intent-display/PRODUCT.md) and
[implementation epic #1065](https://github.com/majiayu000/remem/issues/1065).

## Everyday workflows

### Recall and inspect

```bash
remem search "database encryption"
remem search "deployment decision" --branch main --explain
remem show <memory-id>
remem why <memory-id>
remem current <state-key>
```

`remem search` keeps the terminal clean: per-query `[INFO] [search-perf]`
diagnostics are written to the log file, not stderr, in normal use. Set
`REMEM_DEBUG=1` to mirror them to stderr while debugging.

### Project aliases for Git worktrees

When a worktree has its own project key, preview an alias to the main checkout,
then apply it after checking the paths and Git proof:

```bash
remem project alias add /path/to/worktree --canonical /path/to/main \
  --actor you --reason "same project"
remem project alias add /path/to/worktree --canonical /path/to/main \
  --actor you --reason "same project" --apply
remem project alias list
remem search "decision" --project /path/to/main
remem project alias revoke /path/to/worktree \
  --actor you --reason "worktree retired" --apply
```

The main checkout must already have a project row from normal remem capture.
The alias keeps historical rows at their recorded paths while CLI and MCP
project searches include the worktree's memories. `add` and `revoke` preview
without database writes unless `--apply` is present. Revocation removes the
worktree from the main project's search scope; `list` reports active aliases
with the actor and reason from their latest activation.

Agents can use MCP `search` for compact results, then `get_observations` for
selected details. Use raw recall only when curated memory misses exact
transcript evidence:

```bash
remem raw search "exact phrase" --since 2026-06-01 --json
```

List complete host-bound sessions before reading an exact transcript:

```bash
remem raw sessions --latest 20 --json
remem raw messages --host codex-cli --source-root local \
  --project "/path/to/project" --session-id SESSION_ID --json
remem ingest-sessions --root codex-cli:archive=/path/to/sessions --json
```

Default transcript scans use `$CLAUDE_CONFIG_DIR/projects` and
`$CODEX_HOME/sessions`, falling back to `~/.claude` and `~/.codex`.
An explicitly empty override is an error. Explicit override directories must exist
and be readable; only absent inferred defaults are skipped. Explicit `--root` directories remain
supported; descendant `subagents` directories are excluded from batch scans.
Codex session modes use native source evidence: IDE is interactive, explicit
`exec` is unattended even with a Desktop originator, and subagent evidence
takes precedence. These are source labels, not proof of who initiated a run.
Existing saved modes upgrade once after checking the original classification
evidence; genuine provenance conflicts still fail the batch. This adds schema
v093: retain a database backup before upgrading; older binaries cannot open
the upgraded schema. Raw message identities and cursors are preserved.

Copy `host`, `source_root`, `project`, and `session_id` unchanged from one
`raw sessions` summary into `raw messages`. Existing scripts must add the
required `--host` selector and replace `--root LABEL=PATH` with
`--root HOST:LABEL=PATH`; the same root format applies to `raw reconcile`.
The JSON envelope reports `excluded_legacy_rows`, `excluded_legacy_sessions`,
and `excluded_legacy_identities` when some archive rows cannot enter the
host-bound session contract. Each listed session also carries additive nullable
`mmdd`, `session_intent`, `session_topic`, `display_label`, and
`session_intent_source` fields. `mmdd` is derived from the session created epoch
in Asia/Shanghai; the full `{MMDD}｜{INTENT}｜{topic}` label is present only when
both intent and topic are known. Stop summaries may fill those fields with
source `summary`; unknown, empty, too-long, or redacted values abstain instead
of blocking the rest of the summary. Automatic Stop rollups preserve manual
label overrides, including explicit clears, across later turns. Listing still returns healthy sessions;
`--latest N` fills that bound from healthy sessions only and does not let
unresolved rows occupy those slots. Use the skipped identities (`source_root`,
`project`, `session_id`, and `host` when known) to inspect or repair those
rows. Exact `raw messages` for a skipped selector stays fail-closed. Do not
re-ingest a skipped row unless ingest can actually claim it — many legacy
rows have no trusted host provenance.
`HOST` is `claude-code` or `codex-cli`, and `LABEL` becomes the persisted
`source_root`. Cursor snapshot evidence requires a manually configured and
verified `remem summarize --host cursor` Stop integration; filesystem `--root`
ingestion and reconciliation reject `cursor` explicitly.

### Review and govern

```bash
remem review list
remem review approve <candidate-id>
remem memory suppress memory:<id> --reason "no longer relevant"
remem govern --action stale --dry-run --json <id>
```

Mutating governance commands expose previews, explicit confirmations, or
review boundaries according to their risk. Run `remem <command> --help` for
the current contract instead of relying on a copied command inventory.

MCP tools share that store with stricter wire contracts. The canonical MCP
contract is [GH981](docs/specs/GH981/PRODUCT.md), including the #1061
mutation and scope boundary:

- `save_memory`: pass `host` when the calling host is known. An omitted host is
  recorded as `unknown`, never inferred as `codex-cli`.
- `govern_memory`: dry-run first to preview IDs and current versions from that
  governance transaction. Non-dry-run mutations require `expected_versions`
  for every ID, `confirm_destructive=true`, and an explicit reason.
- `recall_user_context`: supply `project` or `cwd`. The server does not infer
  this scope from its own process working directory.

The local [Remem app](plugins/remem/apps/remem/README.md#correct-session-and-workstream-labels)
shows session/workstream labels or explicit abstention. Sessions can be filtered
by intent and created date in Asia/Shanghai. Operators can correct labels in
batches with a Before/After preview, explicit confirmation, and an audit;
workstream identity and host conversation titles stay stable.

### Configure memory AI and retrieval

```bash
remem config show
remem model current
remem model use balanced --dry-run
remem embedding status
remem embedding download --model multilingual-e5-small
remem embedding backfill --limit 1000
```

`auto` embedding mode stays local unless a remem-specific API key is selected.
The verified local model is optional; the labeled feature-hash fallback remains
available. The second-stage local reranker is also optional and disabled until
configured.

Use the [current configuration routes](docs/README.md#configuration), the
[local embedding contract](docs/specs/local-semantic-embedding/PRODUCT.md), and
`remem config`, `remem embedding`, or `remem reranker` help for details.

### Share or edit memory outside the database

<!-- remem-doc-contract:current-project-export:start -->
```bash
remem sync-memory --cwd .
remem export --markdown --output ./remem-memory
remem export --pack .remem-pack
```
<!-- remem-doc-contract:current-project-export:end -->

Markdown mirrors are human-editable. Project memory packs are deterministic,
git-committable exports with provenance-aware import and quarantine behavior.
See the [memory usage guide](docs/memory-usage-guide.md) and
[project memory pack contract](docs/specs/project-memory-pack/PRODUCT.md).

## Evidence and benchmarks

The checked-in public suite separates memory-system capability evidence from
coding-agent outcome evidence. Verify it locally with:

```bash
cargo run -- bench verify --root eval/public --json-out /tmp/remem-bench-verify.json
```

Verification resolves `claims/registry.json` beside the parent of `--root`, so
an external bundle keeps `public/` and `claims/` as siblings and is independent
of the caller's working directory.

Public adversarial SQLite snapshots are capped at 64 MiB and must be canonical
`VACUUM` images; verifier-consumed artifact targets must also resolve inside the
declared public root.

The current public report does not support public benchmark claims and is
deliberately labeled
`directional_only_no_public_claim`. The historical isolated coding baseline is
useful engineering evidence, but its preloaded-memory condition is not
comparable with the current SessionStart retrieval path.

Reproduction commands, artifact schemas, claim boundaries, and current gates
live in:

- [eval/README.md](eval/README.md)
- [eval/public/README.md](eval/public/README.md)
- [eval/coding-bench/README.md](eval/coding-bench/README.md)

README claims intentionally exclude unsealed local metrics that have no
checked-in report.

## Security and privacy

- Fresh installs create a SQLCipher-encrypted database and private key file.
- The data directory and key use restrictive per-user permissions.
- The REST API binds to `127.0.0.1` and requires a bearer token.
- Hook-captured event previews are redacted before durable storage.
- MCP and CLI workstream listings project redacted text: credential-like
  assignments, short inline secrets, and sensitive command options are replaced
  with `[REDACTED]` in returned fields (and CLI `--json` envelope `project`),
  while ordinary filesystem project paths stay readable. Stored workstream rows
  keep their canonical values for matching and scope checks, so queried output
  can differ from the database when secrets were present.
- Memory candidates and injected content pass secret and poisoning defenses.
- `remem doctor` reports encryption, plaintext residue, schema, and audit
  failures without printing memory payloads.

Read [SECURITY.md](SECURITY.md) for reporting and security policy. Operational
contracts for [SQLite tuning](docs/specs/GH949/PRODUCT.md) and
[memory-poisoning defense](docs/specs/memory-poisoning-defense/PRODUCT.md) are
kept outside the landing page.

## REST API

```bash
remem api --port 5567
TOKEN=$(cat ~/.remem/.api-token)
curl -H "Authorization: Bearer $TOKEN" http://127.0.0.1:5567/api/v1/health
curl -H "Authorization: Bearer $TOKEN" http://127.0.0.1:5567/api/v1/capabilities
```

Clients should feature-detect through `/api/v1/capabilities`. The current
endpoint and compatibility contract is maintained in
[docs/specs/SPEC-web-api.md](docs/specs/SPEC-web-api.md).

## Documentation

Use [docs/README.md](docs/README.md) as the jump page for installation,
configuration, memory lifecycle, retrieval, governance, API, plugin,
operations, architecture, and benchmark material.

The most common destinations are:

- [Architecture and data flow](docs/ARCHITECTURE.md)
- [Memory usage guide](docs/memory-usage-guide.md)
- [Memory lifecycle](docs/memory-lifecycle.md)
- [Codex plugin](plugins/remem/README.md)
- [REST API contract](docs/specs/SPEC-web-api.md)
- [Current spec index](docs/specs/README.md)
- [Changelog](CHANGELOG.md)
- [Contributing](CONTRIBUTING.md)

## Uninstall

Preview and remove host hooks and MCP registration without deleting memory:

```bash
remem uninstall --dry-run
remem uninstall
```

The encrypted database remains in the configured `REMEM_DATA_DIR`. Back it up
before manually deleting that directory if data removal is intended. Ordinary
file deletion removes remem's local data but does not guarantee secure erasure
from filesystem snapshots, backups, or the underlying storage media.

## License

MIT