OpenMem

OpenMem

[!CAUTION] Context management is leaving OpenMem. Smart compaction, the LiteLLM context proxy, and the OpenCode trim plugin in this repo are deprecated here and moving to Smarter Compact (docs, npm install -g smarter-compact). Use OpenMem for memory (providers, indexer, memory_* MCP). Existing OpenMem stacks can still enable the compose context-proxy profile; new context work belongs in Smarter Compact.

OpenMem. Pluggable memory providers (Hindsight, mem0, Cognee) and one setup wizard for coding-agent memory — retain, recall, and index your sources.

A. Memory: your sources become memory any agent can query.

B. Context management (deprecated in OpenMem — use Smarter Compact instead): long sessions stay under the limit; nothing is summarized away.

Benchmarks (context — deprecated here): In seed-matched ContextBench log tasks on Haiku 5.5, smart compaction scored 0.469 higher than keep-everything (95% bootstrap interval 0.339–0.578; eight pairs). Methods and charts still live in this repo (redirect · evidence plan); ongoing product docs and install are on Smarter Compact.

Docs: bcmyguest.github.io/openmem/

MCP: npx -y -p @bcmyguest/openmem openmem-mcp (after the wizard — it needs a running provider)

Start here: Concepts · Quickstart · Compatibility · Development (clone, tests, prek)

Quickstart

From a git clone: Development guide (npm install, npm run setup, tests, prek).

Needs (wizard): Docker Compose v2, Node ≥ 24, and an LLM route for Hindsight — see Quickstart.

Later: npx @bcmyguest/openmem up / down / switch <provider> --yes / doctor.

Wizard dry-run (what first setup plans — no writes):

Full guide: Quickstart · Concepts · Architecture

Architecture

The two diagrams at the top show memory (A) and context management (B; deprecated in OpenMem, see Smarter Compact).

Same diagrams as Mermaid

flowchart LR
  S["<b>Sources</b><br/>Git repos: docs, code outlines<br/>Obsidian vaults · notes · papers · bookmarks<br/>RSS · OpenAlex feeds"] -->|index| I["<b>OpenMem indexer</b><br/>polls repos, watches folders"]
  I -->|retain| P[("<b>Memory provider</b><br/>one active, swappable<br/>Hindsight (default) · mem0 · Cognee · …")]
  P <--> M["<b>OpenMem MCP</b><br/>memory_recall · memory_add<br/>memory_search · memory_reflect<br/>memory_pages_* + export/import, status…"]
  M <-->|tools| A["<b>Coding agents</b><br/>Claude Code · Codex · Cursor · OpenCode"]
  A -.->|"session hooks: recall at start · retain at stop"| M
  classDef om fill:#e8eaf9,stroke:#4651a6,color:#1b1d2a
  class I,M om

flowchart LR
  A["<b>Coding agent</b><br/>Claude Code · Codex · OpenCode 1"] -->|requests| X["<b>Context proxy</b><br/>LiteLLM pre-call hook<br/>trims at 125k tokens (Haiku 95k) · no LLM call"]
  X -->|trimmed request| API["<b>Model API</b><br/>Anthropic · ChatGPT (Codex)"]
  X -->|every turn| S[("<b>Session store</b><br/>SQLite · every turn, verbatim")]
  S -->|"MCP: smart_compact_search · smart_compact_sql"| A
  O["<b>OpenCode 2</b><br/>native plugin, no proxy"] -.->|same store| S
  classDef om fill:#e8eaf9,stroke:#4651a6,color:#1b1d2a
  class X,S om

Native compaction replaces history with an LLM summary, so exact values can be lost; smart compaction keeps every turn verbatim and searchable. Context trimming in OpenMem is deprecated — use Smarter Compact (smarter-compact enable). Legacy stack path: context proxy redirect. See architecture for memory runtime paths and provider-specific behavior.

Providers and portability

• Providers — Provider status lists every provider and its support level from the manifests. Contributor details: adding a provider.
• MCP — unified memory_* plus optional native/NotebookLM servers: MCP setup.
• Context management (deprecated in OpenMem) — moved to Smarter Compact; OpenMem page is a redirect.
• Portable memory — memory_export / memory_import speak PMM: Portable memory.
• Switch — npx @bcmyguest/openmem switch <provider> does not migrate data by itself; export/import (or re-index) moves content.

Compose runs the shared indexer and the services required by the selected provider. Hindsight uses litellm and hindsight (127.0.0.1:8888); mem0 and Cognee use their own APIs and do not include LiteLLM by default. LiteLLM can also be added for memory_reflect synthesis on mem0/Cognee, or to host the optional context proxy's pre-call hook. See Architecture for runtime paths.

Inspiration and related

OpenMem is not affiliated with these projects; they shape the problem or the pattern.

Research notes and benchmark results for the context proxy: Context research.

More setup analogues: Pluggable memory providers.

Formerly personal-memory. Use the openmem CLI and MCP server name; installers drop the old personal-memory MCP entry.

References

Papers and preprints cited in our context-management work (full list):

Reports and blogs (Context Rot, Letta LoCoMo, Anthropic context engineering): references.md.

License

Apache License 2.0 — see LICENSE (Copyright 2026 B Guest).

Contributing

Contributions are welcome. See CONTRIBUTING.md and the development guide for tests and CI.