openmem-mcp
OpenMem MCP provides pluggable coding-agent memory plus legacy session-context inspection tools.
Resolve the correct project bank/scope from a workspace path instead of guessing.
Store, search, recall, and synthesize answers from durable memories, with provider and async ingest status.
Delete memories, export/import in PMM format, and consolidate provider indexes after bulk ingest.
List, search, and read Hindsight knowledge pages and capture approved initiatives/plans before coding.
Inspect stored session context: search trimmed messages, retrieve compressed tool results, run read-only SQL over session databases, and check context-management health.
Indexes Obsidian vaults as memory sources, allowing notes from Obsidian to be retained and updated in the configured memory backend.
Supports Ollama as an LLM route for Hindsight memory stacks, enabling local model-backed reflection and synthesis.
Supports OpenAI-compatible LLM endpoints as a model route for Hindsight memory stacks, enabling reflection and synthesis.
OpenMem
Context management moved to Smarter Compact. OpenMem 0.10 removed its context proxy, session store, smart_compact_* tools and OpenCode 2 trim. OpenMem covers memory: providers, the indexer, memory_* MCP tools and coding-agent hooks. For trimming long sessions, install Smarter Compact (docs).
OpenMem. Pluggable memory providers (Hindsight, mem0, Cognee) and one setup wizard for coding-agent memory — retain, recall, and index your sources.
Your sources become memory any agent can query.
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
Step | Command |
1. Wizard |
|
2. Check |
|
3. Coding agents |
|
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
Related MCP server: mem0-mcp
Architecture
The diagram at the top shows the memory flow.
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 omSee 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.Portable memory —
memory_export/memory_importspeak 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. See Architecture for runtime paths.
Inspiration and related
OpenMem is not affiliated with these projects; they shape the problem or the pattern.
Inspiration for a vendor-agnostic interface + pluggable providers (there: feature flags; here: coding-agent memory). | |
One CLI over many backends; declarative config and tasks without replacing each tool’s own settings. | |
Model proxy used on Hindsight stacks. | |
Reference implementation for knowledge pages, initiative capture and ingest status; OpenMem's hooks replace it in | |
Compresses shell command output before the agent sees it; | |
Bridges a Claude subscription to an Anthropic-compatible API; optional Hindsight model backend (guide). | |
The agent hook and plugin APIs OpenMem translates between (compatibility). |
More setup analogues: Pluggable memory providers.
Formerly personal-memory. Use the
openmemCLI and MCP server name; installers drop the oldpersonal-memoryMCP entry.
References
Papers and preprints on agent memory (full list):
Reference | Link |
MemGPT (Packer et al., 2023) | |
LoCoMo (An et al., 2024) | |
LongMemEval (Wu et al., 2024) | |
MemoryAgentBench (2025) |
Reports: references.md. Context-management references moved to Smarter Compact.
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.
Available Tools
15 toolsmemory_addStore a memoryA
Store durable facts, decisions or session notes in the active provider. Pass bank from memory_project_scope for project work. Hindsight ingests async by default.
Inputs: content (required), bank, async, metadata.
memory_capture_initiativeCapture an initiativeA
Record an approved feature plan as a knowledge page before writing code; relates_to_page_id records a plan change. Skip bug fixes and small tweaks. Hindsight only.
Inputs: title (required), summary (required), bank, relates_to_page_id.
memory_consolidateConsolidate / cognifyA
Rebuild the provider's graph or index after bulk ingest (Cognee cognify; no-op on mem0).
Inputs: bank.
memory_exportExport memories (PMM)ARead-onlyIdempotent
Export memories as PMM v1 JSON or JSONL for backup or migration. Pass bank for large stores.
Inputs: bank, format.
memory_forgetDelete memoriesADestructiveIdempotent
Delete memories: mem0 needs memory_id; on Hindsight a bank without memory_id drops the whole bank. Confirm with the user first. Not available on Cognee.
Inputs: bank, memory_id.
memory_importImport memories (PMM)A
Import a PMM v1 payload from memory_export. Content and scope carry over; embeddings and graphs do not.
Inputs: data (required), merge_strategy.
memory_pages_listList knowledge pagesARead-onlyIdempotent
List a bank's knowledge pages (ids, names, folders; no bodies). Hindsight only.
Inputs: bank.
memory_pages_readRead a knowledge pageARead-onlyIdempotent
Read one knowledge page by id (from a page listing, search, or [[page:]] link). Hindsight only.
Inputs: page_id (required), bank.
memory_pages_searchSearch knowledge pagesARead-onlyIdempotent
Search knowledge pages: past decisions and conventions. Check them before fixing a bug, changing a test or building something; verify claims against the code. Hindsight only.
Inputs: query (required), bank, limit.
memory_project_scopeResolve project bankARead-onlyIdempotent
Resolve the project bank (user_id / dataset) and access policy for a workspace path. Call it instead of guessing a bank name. Local mapping only.
Inputs: cwd.
memory_provider_statusProvider statusBRead-onlyIdempotent
Report the active provider id and backend URL.
Inputs: no named parameters.
memory_recallRecall context for a questionBRead-onlyIdempotent
Retrieve stored context for a natural-language question (Hindsight recall; search on mem0 and Cognee).
Inputs: query (required), bank, limit.
memory_reflectReflect / synthesize an answerARead-onlyIdempotent
Synthesize a reasoned answer from stored memories, with evidence. The answer is not stored.
Inputs: query (required), bank, limit.
memory_searchSearch memoriesARead-onlyIdempotent
Return ranked raw hits from stored memories. memory_recall suits questions; memory_reflect synthesizes an answer.
Inputs: query (required), bank, limit.
memory_statusIngest statusARead-onlyIdempotent
Report whether async ingest has drained (ready, active and failed counts, memory_add operation ids). Check before recalling just-stored content. Hindsight only; mem0 is always ready.
Inputs: bank, operation_ids.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 15 tools
The three retrieval tools (search/recall/reflect) overlap conceptually, but each description explicitly says when to use which (raw hits vs. context vs. synthesized answer), which resolves most of the confusion. memory_status vs. memory_provider_status are also close (ingest drain vs. provider id/URL) but are distinguishable by their stated outputs; memory_add vs. memory_import is clear from the PMM payload requirement.
Every name uses the memory_ prefix in snake_case, giving a strong shared convention. The only deviation is word order: memory_pages_list/search/read put the verb last while memory_add, memory_search and memory_forget put it directly after the prefix, so the pattern is predictable but not perfectly uniform.
15 tools sits at the top of the sensible band and is justified by the breadth of the surface: three provider backends, ingest lifecycle, pages and export/import. Nothing looks like filler, though the provider-specific optionality (Hindsight-only, mem0-only, Cognee-only tools) means several tools are dead for any given user.
Storage, retrieval, sync, backup and page reading are covered, but there are clear gaps: no memory_update/overwrite tool, and knowledge pages can be listed, searched and read but not edited or deleted except by dropping a whole bank via memory_forget. Page creation exists only through memory_capture_initiative for feature plans, so an agent cannot add or revise a convention page directly.
Maintenance
Related MCP Connectors
Shared memory for coding agents. Stop re-explaining your codebase every session.
Universal memory for AI agents and tools. Save, organize and search context anywhere.
Memory for AI agent teams across tools, sessions, repositories, and teammates.
Shared, scoped, reviewable team memory for AI coding agents.
Related MCP Servers
- AlicenseAqualityBmaintenanceMemory manager for AI apps and Agents using various graph and vector stores and allowing ingestion from 30+ data sources633,348Apache 2.0

mem0-mcpofficial
AlicenseAqualityDmaintenanceSelf-hosted Mem0 MCP server integrating Qdrant, Neo4j, and Ollama for semantic memory search, graph entity relationships, and memory management via OpenMemory API.64MIT- AlicenseAqualityBmaintenanceProvides persistent, searchable memory across AI coding agent and chat history (Claude Code, Codex, Gemini CLI, ChatGPT, and more) via retrieval-augmented generation, enabling semantic and hybrid search to retain context across sessions.5MIT
- AlicenseNot gradedqualityDmaintenanceConsolidates git history, test results, and Copilot sessions into a searchable SQLite database for AI assistants to answer questions about development activity.6MIT