AutoGineer
Generated banner for memoria
Generated logo for memoria

memoria

Memory frameworkOfficial Matrix Origin project

Created by Matrix Origin

Published in matrixorigin/memoria. Publisher page

626 GitHub stars

What it is

Secure memory management for AI Agents • Ensures data integrity • Reduces hallucinations • Maintains consistent long-term context
— the description by Matrix Origin

AutoGineer overview, from the brain’s own files

Memoria is a persistent memory layer designed to give AI agents reliable, auditable, and version-controlled long-term memory. By leveraging a Git-inspired architecture powered by MatrixOne, it allows agents to snapshot, branch, merge, and rollback their memory state. This ensures that memory changes are tracked and reversible, reducing hallucinations and maintaining consistency across sessions. It supports semantic search through hybrid retrieval and includes self-governing features to detect contradictions and maintain audit trails, making it a robust solution for managing agent knowledge.

How it works

Memory model: Hybrid

AutoGineer overview, from the brain’s own files

Memoria functions as a memory service that agents interact with via MCP tools. It uses a hybrid memory model where facts, preferences, and decisions are stored and retrieved. The system supports branching for isolated experimentation, allowing agents to test new information or hypotheses without altering the main memory state. It includes specific steering rules for managing the lifecycle of memories, from initial retrieval at the start of a conversation to purging transient working memories upon task completion. Data is stored using a database-native engine that supports zero-copy branching and snapshots.

Folders
FolderRoleFiles
.claudeagent-config1
.cursoragent-config2
.geminiagent-config1
.githubagent-config16
.kiroagent-config7
assetsattachments7
docsdocs10
scriptsscripts2
skillsagent-instructions7
benchmarksfolder7
configfolder7
grafanafolder1
memoriafolder280
pluginsfolder69
sdkfolder36

Requirements

Apps: Docker

Databases: PostgreSQL, SQLite

API keys (by name): MEMORIA_API_KEY, MEMORIA_EMBEDDING_API_KEY, MEMORIA_LLM_API_KEY

Works with: Claude Code, Cursor, Gemini CLI, Kiro

Set it up

  1. This brain runs code automatically: 5 scripts. Review README.md, scripts/install.ps1, scripts/install.sh before opening the folder in Claude Code. No step below turns a hook on for you.

    • README.md: curl -sSL https://raw.githubusercontent.com/matrixorigin/Memoria/main/scripts/install.sh | bash
    • README.md: curl -sSL https://raw.githubusercontent.com/matrixorigin/Memoria/main/scripts/install.sh | bash
    • README.md: command -v memoria >/dev/null || curl -sSL https://raw.githubusercontent.com/matrixorigin/Memoria/main/scripts/install.sh | bash -s -- -y -d ~/.local/bin
    • scripts/install.ps1: pwsh scripts/install.ps1
    • scripts/install.sh: sh scripts/install.sh
  2. Not scanned by AutoGineerThe author’s README also describes installing it with Docker Compose. Read its install section: AutoGineer did not scan that path. https://github.com/matrixorigin/memoria/blob/93ccccf2ea8da4c205ac2d93c1a010c287bc742d/README.md#-quick-start
  3. Not scanned by AutoGineerThe author’s README also describes installing it from a clone of its repository. Read its install section: AutoGineer did not scan that path. https://github.com/matrixorigin/memoria/blob/93ccccf2ea8da4c205ac2d93c1a010c287bc742d/README.md#-quick-start

  4. Created by Matrix Origin. Published in matrixorigin/memoria. Licence: Apache License 2.0.

Usage

AutoGineer overview, from the brain’s own files

  • Persistent memory across agent sessions
  • Git-like version control for agent knowledge
  • Isolated experimentation via memory branching
  • Semantic and full-text hybrid retrieval
  • Automated contradiction detection and memory governance
“Let's try switching from PostgreSQL to SQLite.”
The agent creates a new memory branch 'eval_sqlite', performs experiments, and allows the user to diff and merge the results back to main.
“I want to add OAuth support to the API.”
The agent searches for existing goals, stores the new goal, and tracks progress as working memories across sessions.
“What are my deployment preferences?”
The agent retrieves relevant semantic memories to provide context-aware information based on previous sessions.

Documentation by Matrix Origin

<div align="center"> <img src="assets/memoria-logo.png" alt="Memoria Logo" width="300"/>

Memoria

The World's First Git for AI Agent Memory

Snapshot · Branch · Merge · Rollback — for memory, not code.

Git made code safe to change. Memoria makes memory safe to change.

Image: CI Image: Release Image: GitHub Stars Image: Downloads Image: License Image: MCP Image: MatrixOne Image: Paper

Quick Start · Memoria in Astra · Why Memoria · Research · See It in Action · API Reference · Architecture · Development · Citation

</div>

Overview

Memoria is a persistent memory layer for AI agents with Git-level version control. Every memory change is tracked, auditable, and reversible — snapshots, branches, merges, and time-travel rollback, all powered by MatrixOne's native Copy-on-Write engine.

A core memory component of MatrixOrigin's Astra.

Astra runs the agent. Memoria helps it remember across sessions. MatrixOne powers the data storage and search.

Using Astra? · Use Memoria with another agent

<table> <tr> <td align="center" width="33%">

🔀 Git for Memory

Zero-copy branching, instant snapshots, point-in-time rollback — version control for every memory mutation

</td> <td align="center" width="33%">

🔍 Semantic Search

Vector + full-text hybrid retrieval finds memories by meaning, not just keywords

</td> <td align="center" width="33%">

🛡️ Self-Governing

Auto-detects contradictions, quarantines low-confidence memories, maintains audit trails

</td> </tr> </table>

<table> <tr> <td align="center" width="33%">

🔒 Private by Default

Local embedding model option — no data leaves your machine

</td> <td align="center" width="33%">

🧠 Cross-Conversation

Preferences, facts, and decisions persist across sessions

</td> <td align="center" width="33%">

📋 Full Audit Trail

Every memory mutation has a snapshot + provenance chain

</td> </tr> </table>

Supported Agents

<p align="center"> <a href="https://kiro.dev"><img src="https://img.shields.io/badge/Kiro-00C853?style=for-the-badge&logo=data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHZpZXdCb3g9IjAgMCAyNCAyNCI+PHRleHQgeD0iNCIgeT0iMTgiIGZvbnQtc2l6ZT0iMTYiIGZpbGw9IndoaXRlIj5LPC90ZXh0Pjwvc3ZnPg==&logoColor=white" alt="Kiro"/></a> <a href="https://cursor.sh"><img src="https://img.shields.io/badge/Cursor-000000?style=for-the-badge&logo=cursor&logoColor=white" alt="Cursor"/></a> <a href="https://docs.anthropic.com/en/docs/claude-code"><img src="https://img.shields.io/badge/Claude_Code-D97757?style=for-the-badge&logo=anthropic&logoColor=white" alt="Claude Code"/></a> <a href="https://openai.com/index/introducing-codex/"><img src="https://img.shields.io/badge/Codex-412991?style=for-the-badge&logo=openai&logoColor=white" alt="Codex"/></a> <a href="https://geminicli.com"><img src="https://img.shields.io/badge/Gemini_CLI-4285F4?style=for-the-badge&logo=google&logoColor=white" alt="Gemini CLI"/></a> <a href="plugins/openclaw/README.md"><img src="https://img.shields.io/badge/OpenClaw-FF6B6B?style=for-the-badge" alt="OpenClaw"/></a> <a href="plugins/hermes/README.md"><img src="https://img.shields.io/badge/Hermes-8B5CF6?style=for-the-badge" alt="Hermes"/></a> </p>

<p align="center"><i>Works with any MCP-compatible agent</i></p>

🧠 Memoria in Hermes

Memoria is available from the Hermes plugin catalog. Log in at Memoria and create/copy a memory-service API key, then run:

hermes plugins install memoria --yes-deps --enable
hermes memory setup
hermes memory status

In the interactive setup, select memoria, paste your API key at the masked prompt, and choose whether to enable automatic capture (off by default). Confirm that status reports memoria, installed and available, then exit any existing conversation and start a new one with hermes. Status checks local readiness; verify a live write using the complete Hermes guide. The free Memoria Cloud requires no local Memoria server or database. Self-hosting, fixed GitHub installation and named profiles are covered in the same guide.

🧩 Memoria in Astra

In Astra, Memoria stores and retrieves facts, preferences, decisions, and session summaries so agents can reuse knowledge across conversations. Memory changes can be reviewed and rolled back.

How you use itWhere to start
Hosted AstraMemoria is already running for you. Follow the Astra quick start.
Self-hosted AstraAstra's deployment includes compatible Memoria and MatrixOne services. Follow Astra's Docker setup.
Memoria with other agentsUse Memoria independently via MCP. Follow the Memoria quick start below.

For example, search your memories from Astra:

astra memory search "deployment preferences"

🚀 Quick Start

<details open> <summary><b>☁️ Memoria Cloud (Recommended — no Docker, no database)</b></summary> <br/>

1. Sign up at thememoria.ai and get your token

2. Install & configure

curl -sSL https://raw.githubusercontent.com/matrixorigin/Memoria/main/scripts/install.sh | bash
cd your-project
memoria init -i   # Select "Remote" mode, paste your token

3. Restart & verify — restart your AI tool, then ask: "Do you have memory tools available?"

</details>

<details> <summary><b>🐳 Self-Hosted (Docker — full data control)</b></summary> <br/>

# 1. Start MatrixOne + API
git clone https://github.com/matrixorigin/Memoria.git
cd Memoria
docker compose up -d

# 2. Install CLI
curl -sSL https://raw.githubusercontent.com/matrixorigin/Memoria/main/scripts/install.sh | bash

# 3. Configure your AI tool
cd your-project
memoria init -i   # Select "Embedded" mode

Restart your AI tool, then ask: "Do you have memory tools available?"

</details>

<details> <summary><b>🦞 OpenClaw Plugin</b></summary> <br/>

Use the native OpenClaw plugin: OpenClaw Plugin Setup

# ensure memoria CLI exists
command -v memoria >/dev/null || curl -sSL https://raw.githubusercontent.com/matrixorigin/Memoria/main/scripts/install.sh | bash -s -- -y -d ~/.local/bin

# install & enable
openclaw plugins install @matrixorigin/memory-memoria
openclaw plugins enable memory-memoria

# cloud-first setup
openclaw memoria setup --mode cloud --api-url <MEMORIA_API_URL> --api-key <MEMORIA_API_KEY> --install-memoria
openclaw memoria health

</details>

Or download binaries directly from GitHub Releases. For detailed setup, see Setup Skill.

💡 Why Memoria?

CapabilityMemoriaLetta / Mem0 / Traditional RAG
Git-level version controlNative zero-copy snapshots & branchesFile-level or none
Isolated experimentationOne-click branch, merge after validationManual data duplication
Audit trailFull snapshot + provenance on every mutationLimited logging
Semantic retrievalVector + full-text hybrid searchVector only
Self-governanceAutomatic contradiction detection & quarantineManual cleanup

🔬 Research Foundation

Memoria's Git-for-Data layer is backed by Version Control System for Data with MatrixOne, our arXiv paper on bringing Git-like workflows directly into a cloud-native database.

The paper describes how MatrixOne's immutable storage and MVCC architecture make clone, branch / tag, diff, merge, and revert practical at terabyte scale without loading whole datasets into memory. Memoria applies the same foundation to AI-agent memory, so every memory change can be isolated, reviewed, merged, or rolled back with database-native consistency.

🎬 See Git for Data in Action

<p align="center"> <img src="assets/git4data-story-writing-demo.svg" alt="Animated Memoria Git-for-Data demo showing an author branching a story draft, merging a better plot direction into the main storyline, and rolling back the last two unsatisfying beats." width="100%"/> </p>

A story-writing scenario demonstrates the core concept: an author has accepted story beats on main, opens an experimental branch for a different plot direction, merges the stronger draft back, and rolls back when the newest beats don't work.

<details> <summary><b>What the demo shows</b></summary>

  • Main storyline — accepted story beats live on main

  • Experimental branch — the author tries a new plot turn without rewriting canon

  • Merge — the stronger draft is promoted back into the main storyline

  • Rollback — the last two bad turns are discarded, and writing resumes from a safe snapshot

</details>

📖 Steering Rules

Steering rules teach your AI agent when and how to use memory tools. Without them, the agent has tools but no guidance — like having a database without knowing the schema.

RulePurpose
memoryCore memory tools — when to store, retrieve, correct, purge
session-lifecycleBootstrap at conversation start, cleanup at end
memory-hygieneProactive governance, contradiction resolution, snapshot cleanup
memory-branching-patternsIsolated experiments with branches
goal-driven-evolutionTrack goals, plans, progress across conversations

File locations: Kiro: .kiro/steering/*.md · Cursor: .cursor/rules/*.mdc · Claude: .claude/rules/*.md · Codex: AGENTS.md · Gemini CLI: GEMINI.md + .gemini/*.md

After upgrading: memoria rules --force

<details> <summary><b>Example: Conversation Lifecycle</b></summary>

┌─────────────────────────────────────────────────────────────────────────────┐
│  CONVERSATION START                                                         │
│  ┌─────────────────────────────────────────────────────────────────────┐   │
│  │ 1. memory_retrieve(query="<user's question>")  ← load context       │   │
│  │ 2. memory_search(query="GOAL ACTIVE")          ← check active goals │   │
│  └─────────────────────────────────────────────────────────────────────┘   │
├─────────────────────────────────────────────────────────────────────────────┤
│  MID-CONVERSATION                                                           │
│  ┌─────────────────────────────────────────────────────────────────────┐   │
│  │ • User states preference → memory_store(type="profile")             │   │
│  │ • User corrects a fact   → memory_correct(query="...", new="...")   │   │
│  │ • Topic shifts           → memory_retrieve(query="<new topic>")     │   │
│  └─────────────────────────────────────────────────────────────────────┘   │
├─────────────────────────────────────────────────────────────────────────────┤
│  CONVERSATION END                                                           │
│  ┌─────────────────────────────────────────────────────────────────────┐   │
│  │ 1. memory_purge(topic="<task>")  ← clean up working memories        │   │
│  │ 2. memory_store(type="episodic") ← save session summary             │   │
│  └─────────────────────────────────────────────────────────────────────┘   │
└─────────────────────────────────────────────────────────────────────────────┘

</details>

<details> <summary><b>Example: Goal-Driven Evolution</b></summary>

You: "I want to add OAuth support to the API"

AI:  → memory_search(query="GOAL OAuth")           ← check for existing goal
     → memory_store(content="🎯 GOAL: Add OAuth support\nStatus: ACTIVE", type="procedural")

     ... works on implementation, stores progress as working memories ...

     → memory_store(content="✅ STEP 1/3: Added OAuth routes", type="working")
     → memory_store(content="❌ STEP 2/3: Token refresh failed — need to fix expiry logic", type="working")

... next conversation ...

AI:  → memory_search(query="GOAL ACTIVE")          ← finds OAuth goal
     → memory_search(query="STEP for GOAL OAuth")  ← loads progress
     "Last time we were working on OAuth. Step 2 failed on token refresh. Want to continue?"

... goal completed ...

AI:  → memory_correct(query="GOAL OAuth", new_content="🎯 GOAL: OAuth — ✅ ACHIEVED")
     → memory_store(content="💡 LESSON: Token refresh needs 5min buffer before expiry", type="procedural")
     → memory_purge(topic="STEP for GOAL OAuth")   ← clean up working memories

</details>

<details> <summary><b>Example: Branch for Risky Experiments</b></summary>

You: "Let's try switching from PostgreSQL to SQLite"

AI:  → memory_branch(name="eval_sqlite")
     → memory_checkout(name="eval_sqlite")

     ... experiments on branch, stores findings ...

     → memory_diff(source="eval_sqlite")     ← preview changes
     → memory_checkout(name="main")
     → memory_merge(source="eval_sqlite")    ← or delete if failed

</details>

📚 API Reference

Core Tools
ToolDescription
memory_storeStore a new memory
memory_retrieveRetrieve relevant memories (call at conversation start)
memory_searchSemantic search across all memories
memory_correctUpdate an existing memory
memory_purgeDelete by ID or topic keyword
memory_listList active memories
memory_profileGet user's memory-derived profile
memory_feedbackRecord relevance feedback (useful/irrelevant/outdated/wrong)
memory_capabilitiesList available memory tools

<details> <summary><b>Snapshots & Branches</b></summary>

ToolDescription
memory_snapshotCreate named snapshot
memory_snapshotsList snapshots with pagination
memory_snapshot_deleteDelete snapshots by name, prefix, or age
memory_rollbackRestore to snapshot
memory_branchCreate isolated branch
memory_branchesList all branches
memory_checkoutSwitch branch
memory_mergeMerge branch back
memory_branch_deleteDelete a branch
memory_diffPreview merge changes

</details>

REST clients can use cached-count snapshot listing to avoid historical count queries and exclude automatic safety snapshots.

<details> <summary><b>Maintenance</b></summary>

ToolDescription
memory_governanceQuarantine low-confidence memories (1h cooldown)
memory_consolidateDetect contradictions (30min cooldown)
memory_reflectSynthesize insights (2h cooldown)

memory_rebuild_index, memory_observe, memory_get_retrieval_params, memory_tune_params, memory_extract_entities, and memory_link_entities are available via REST API but hidden from MCP tool listing — they are ops/debug tools not intended for agent use.

</details>

Memory Types
TypeUse forExample
semanticProject facts, decisions"Uses Go 1.22 with modules"
profileUser preferences"Prefers pytest over unittest"
proceduralWorkflows, how-to"Deploy: make build && kubectl apply"
workingTemporary task context"Currently debugging auth module"
episodicSession summaries"Session: optimized DB, added indexes"

Full API details: API Reference Skill

Retry-safe single-memory writes: Idempotent store protocol.

Trusted adapter content preservation: Content-filter policy.

🔧 Commands

CommandDescription
memoria init -iInteractive setup wizard
memoria statusShow config and rule versions
memoria rulesUpdate steering rules (auto-detect, --tool, or -i)
memoria mcpStart MCP server
memoria serveStart REST API server
memoria benchmarkRun benchmark suite

🤖 For AI Agents

If you're an AI agent helping a user set up Memoria:

  1. Load the Setup Skill — it has step-by-step instructions

  2. Ask before acting: which AI tool? · database mode? · embedding service? (Self-Hosted only)

  3. Run memoria init -i in the user's project directory

  4. Tell user to restart their AI tool, then verify with memory_retrieve("test")

Self-Hosted only: Configure embedding BEFORE first MCP server start — dimension is locked into schema.

🏗️ Architecture

Cloud / Remote Mode:

┌─────────────┐     MCP (stdio)     ┌──────────────────┐     HTTP/REST     ┌──────────────────┐
│  AI Agent   │ ◄─────────────────► │  Memoria CLI     │ ◄──────────────► │  Memoria Cloud   │
│             │   store / retrieve  │  (MCP bridge)    │   Bearer token   │  API Server      │
└─────────────┘                     └──────────────────┘                  └──────────────────┘

Self-Hosted / Embedded Mode:

┌─────────────┐     MCP (stdio)     ┌──────────────────────────────────────┐     SQL      ┌────────────┐
│  AI Agent   │ ◄─────────────────► │  Memoria MCP Server                  │ ◄──────────► │ MatrixOne  │
│             │   store / retrieve  │  ├── Canonical Storage               │  vector +    │  Database  │
│             │                     │  ├── Retrieval (vector / semantic)   │  fulltext    │            │
│             │                     │  └── Git-for-Data (snap/branch/merge)│              │            │
└─────────────┘                     └──────────────────────────────────────┘              └────────────┘

For codebase details, see Architecture Skill.

🛠️ Development

make up              # Start MatrixOne + API
make test            # Run all tests
make release VERSION=0.2.0   # Bump, tag, push

Developer documentation (for contributing to Memoria):

SkillDescription
ArchitectureCodebase layout, traits, tables
API ReferenceREST endpoints, request/response
DeploymentDocker, K8s, multi-instance
Plugin DevelopmentGovernance plugins
ReleaseVersion bump, CI/CD
Local EmbeddingOffline embedding build

📝 Citation

If you use Memoria in academic work, or refer to its Git-for-Data foundation for AI-agent memory, please cite the MatrixOne paper that describes the underlying data version control design:

@misc{gou2026versioncontrolsystemdata,
  title={Version Control System for Data with MatrixOne},
  author={Gou, Hongshen and Tian, Feng and Wang, Long and Deng, Nan and Xu, Peng},
  year={2026},
  eprint={2604.03927},
  archivePrefix={arXiv},
  primaryClass={cs.DB},
  doi={10.48550/arXiv.2604.03927},
  url={https://arxiv.org/abs/2604.03927}
}

🌟 Community

We'd love your support! If Memoria helps you, consider giving us a star.

Image: Star History Chart

Contributing — See the developer documentation above and check out our issue templates for bug reports, feature requests, and more.

License

Apache-2.0 © MatrixOrigin

CHANGELOG.md

Changelog

All notable changes to this project will be documented in this file.

[0.5.2] - 2026-09-11

🐛 Bug Fixes

  • auth: Add owner-scoped master authority (#250) (bc55ee3)

  • openclaw: Ship runnable npm package and preserve search scores (#249) (61001bc)

  • snapshot: Preserve data when restoring pre-subject_id snapshots (#248) (a2e1e25)

  • mcp: Handle ping requests (#237) (6279342)

📚 Documentation

  • Fix broken star history chart (#233) (85f6c3f)

🚀 Features

  • auth: Add scoped API keys for Astra (#244) (58012cf)

Release Notes

  • OpenClaw npm and Python SDK packages use separate release workflows; this release tag does not publish them.

  • The legacy snapshot restore fix does not resolve the MatrixOne upgrade failure observed on v4.2.1-d2393868a-2026-08-28. See compatibility and verification notes before upgrading a production database.

[0.5.1] - 2026-08-26

🐛 Bug Fixes

  • storage: Handle MatrixOne aggregate and nullable parameter compatibility (#239) (54566bc)

👷 CI

  • Increase MatrixOne memory limit (#234) (0e15b55)

[0.5.0] - 2026-08-26

⚡ Performance

  • snapshot: Optimize snapshot listing (#202) (3207091)

🐛 Bug Fixes

  • snapshot: Read SHOW SNAPSHOTS columns case-insensitively for MatrixOne v4.x (#226) (4676239)

  • Warnings in make test command (#221) (63f0289)

  • Release python sdk ci (#207) (37ca1e7)

🚀 Features

  • Restore filtered fulltext memory search (#232) (efd3d65)

  • Add structured memory queries (#228) (ca9394d)

  • Support extra metadata in batch write (#223) (54c9114)

  • Add subject_id isolation and memory_types filtering for retrieve/search (#215) (2446feb)

  • Add memoria python sdk (#206) (a2e659c)

  • Add explicit branch access for memory operations (#203) (7b2b372)

  • memory: Add selective branch pick support (#193) (4d16236)

[0.4.0] - 2026-05-11

🐛 Bug Fixes

  • Trivial fix for pro function (#201) (caa3d79)

📚 Documentation

  • Add citation instructions (#197) (a7c3547)

  • Add MatrixOne research paper reference (#196) (a5d2786)

🚀 Features

  • Group collaboration API with per-member branch isolation (#198) (357d44c)

[0.3.3] - 2026-04-22

🐛 Bug Fixes

  • cli: Normalize MCP tool name; MatrixOne-safe srv_user_stats upsert (#192) (f18069c)

🚀 Features

  • memory: Unify session scope across memory interfaces (#190) (f504989)

  • Add multi-db pool budget sizing (#191) (79c1fb0)

🧪 Testing

  • Migrate API and MCP e2e to multi-db (#189) (b34717d)

[0.3.2] - 2026-04-17

🐛 Bug Fixes

  • multidb: Default fresh deployments to multi-db (#188) (de98df6)

  • storage: Remove routed USE db dependency (#187) (11603af)

[0.3.1] - 2026-04-16

⚡ Performance

  • storage: Harden multi-db pools and speed legacy migration (#180) (3a1c7a2)

🐛 Bug Fixes

  • memory: Enforce strict session retrieval semantics (#185) (1f99f39)

🚀 Features

  • memory: Add session-scoped purge (#186) (07c0e7f)

  • Add ops metrics (#177) (897d6d5)

[0.3.0] - 2026-04-13

⚡ Performance

  • Improve store (#151) (3ef1e04)

  • Improve memory list (#150) (0fdd5bc)

  • Optimize list memories again (#149) (febb16f)

  • Optimize list (#148) (a4d31f7)

  • Async batched edit-log writer with unified flush path (#134) (e3718c2)

  • Optimize db pool usage (#83) (53c0242)

🐛 Bug Fixes

  • runtime: Harden multi-db rollout and metrics rollups (#173) (fbd4d48)

  • Finalize per-user DB isolation rollout (#172) (b1917ef)

  • Migration drops mem_branches on every startup + UTF-8 panic in diff preview (#171) (e1eab73)

  • storage: Use current tenant for account snapshots (#169) (72802c1)

  • ci: Fix npm publish workflow for Linux runners (#164) (9f746ac)

  • openclaw-plugin: Pass OpenClaw security scan by isolating child_process usage (#163) (49a6e4a)

  • Improve pool diagnostics and serialize db verification tests (#159) (3c57be7)

  • No statistical data for the retrieval API called via MCP (#157) (4aa7a00)

  • Big purge (#154) (17265aa)

  • Background governance (#152) (c712384)

  • Null processing workaround due to matrixone 3.0.8 bug (#136) (7c77de1)

  • Multi-table DELETE+LIMIT syntax error and inaccurate index comment in cleanup_orphan_stats (#115) (8553bf0)

  • Isolate DB pools, drop-on-full entity queue, embedding concurren… (#112) (fd92c54)

  • Enable user level metrics (#111) (8f61732)

  • Fail fast when local embedding support is unavailable (#103) (4320764)

  • openclaw: Fail fast for unsupported local embeddings (#85) (0365491)

  • Code agent tool header (#96) (2bb2e2f)

  • Stop words (#77) (1ce8be9)

👷 CI

  • npm: Auto-determine version from npm registry (#165) (89e8281)

  • Mergify: Configuration update (#142) (6e9f5c6)

  • Mergify: Configuration update (#143) (bf2335e)

  • Add GitHub Actions workflow for npm publishing + update npm package version to 0.4.2 (#109) (61cb0d2)

  • Mergify: Configuration update (#107) (a3c3c2a)

  • Mergify: Configuration update (#105) (c43a73d)

📚 Documentation

  • Update README (#146) (cbccd42)

  • Prioritize Memoria Cloud, add Git-for-Memory tagline (#135) (4b68e3b)

  • clawhub: Rename to thememoria + update for api mode (#102) (89a6500)

📦 Miscellaneous

  • Enhance connection pool health monitoring, Prometheus metrics, and load test (#158) (bcd20ab)

  • Add code owners (#147) (10aff34)

  • plugin: Bump to v0.4.1 for npm republish (#104) (f6ee2cc)

  • Cleanup python (#100) (0333063)

🚀 Features

  • Auto-migrate legacy local startup (#178) (0d71169)

  • Support trace binary install count (#174) (885140a)

  • Add autoApprove to generated MCP config (fixes #74) (#170) (ceb97da)

  • storage: Implement per-user DB isolation and migration tooling (#167) (ac1470a)

  • Add user streamable http metrics (#145) (24eda05)

  • Streamable http mcp server (#140) (9b70130)

  • Add Windows x86_64 binary build and PowerShell install script (#133) (04ab5b1)

  • Embedding metrics, Grafana dashboard overhaul & monitoring stack (#137) (597a431)

  • openclaw: Add X-Memoria-Tool header to API requests (#108) (1d013ed)

  • Add gemini cli support (#87) (8e79ced)

  • plugin: Direct HTTP API mode + mem/content leak bug fix + rename to @matrixorigin/thememoria (#101) (fe0e42c)

  • Support multi embedding endpoints (#97) (06f9862)

  • Track per-user tool access times with in-memory cache and periodic DB flush (#94) (bd18be6)

  • openclaw: Cloud/local connect command + fail-safe onboarding (#70) (3b73268)

[0.2.3] - 2026-03-21

⚡ Performance

  • Fix performance issues (#73) (b64de86)

📚 Documentation

  • readme: Polish beat card spacing and idea bulb icon (#69) (c88cccc)

  • Add Git for Data story demo (#66) (2d71edb)

🚀 Features

  • Add ClawHub Memoria skill bundle (#71) (7b4034a)

  • Distributed Deployment: Health Checks, Pool Metrics, OpenTelemetry, Grafana Dashboard (#67) (cd77c9e)

🧪 Testing

[0.2.2] - 2026-03-20

🐛 Bug Fixes

  • Security and snapshot count (#61) (eafed50)

  • Flaky ci test (#58) (c788dc0)

🚀 Features

  • Feedback system, adaptive retrieval, governance audit trail, API hardening, and comprehensive e2e tests (#65) (539fd8a)

  • Add --tool flag to mcp subcommand and fix codex support (#64) (1701094)

  • Interactive init prefill, Codex support, self-update, install auto-init (#63) (6394d8d)

  • Enable apikey authentication (#47) (18c6c17)

[0.2.1] - 2026-03-19

🏗️ Build

  • ci: Switch Linux release binaries to musl static linking (#56) (b651cd1)

📚 Documentation

  • openclaw: Simplify install path and clarify success checks (#57) (1e5a5f3)

🚀 Features
🧪 Testing

  • Add session consistency test (#54) (27bf9f8)

[0.2.0-rc] - 2026-03-19

🐛 Bug Fixes

  • Update README logo to new memoria-logo asset (#52) (7d1245f)

  • UTF-8 string truncation panic with multi-byte characters (#48) (f774499)

  • Install.sh Text file busy error when upgrading (#46) (a79f971)

🚀 Features

  • benchmark: Separate official LongMemEval and BEAM reporting (#50) (72998fe)

  • Add OpenClaw-native Memoria onboarding (#49) (7560190)

  • Implement plugin framework (#45) (4301f97)

  • Replace hand-rolled prompts with cliclack TUI wizard (#44) (ef071bd)

[0.1.0] - 2026-03-18

🐛 Bug Fixes

  • Install.sh latest URL format (/releases/latest/download/ not /releases/download/latest/) (ddbd06e)

  • Docker release username (#43) (18ebca5)

🚀 Features

  • cli: Connectivity checks for DB and embedding in interactive init (#42) (aedb529)

  • Interactive setup wizard (memoria init -i) and improved install script (#41) (e0df7b9)

[0.1.0-rc2] - 2026-03-17

🐛 Bug Fixes

  • Missing from rust refactor (#39) (fb38d6c)

[0.1.0-rc1] - 2026-03-17

Sync

  • Update to v0.2.5 - auto table creation, embedding dim switching (0379674)

⚡ Performance

  • Small opts (#27) (2e9af19)

  • Enhance explain (#26) (cf60fce)

  • Improve memory retrieval and graph operations (#21) (aa50616)

🐛 Bug Fixes

  • Cross toml (f7d24ad)

  • Cross compiling env (#38) (3b35ac1)

  • Release dep (#36) (5c7b347)

  • Remove hardcoded version in memoria-git dependency (#35) (5b142e6)

  • Ci related (#34) (e1b7e0c)

  • Hybrid search (#30) (e1f319f)

  • Issue #22. (#23) (068dda3)

  • Batch inject (#24) (85c4675)

  • Sync version to 0.1.14 and remove 500-char limit in rule version… (#20) (ad84469)

  • Stale graph node retrieval and cooldown cache pollution (#15) (b1dd0b3)

  • Resolve branch name hyphen bug, add input validation, optimize CI workflows (#8) (cc82cf9)

📚 Documentation

  • Add CPU-only PyTorch installation guide for non-GPU environments (#12) (8e1af3a)

  • Guide users to edit config files after init if needed (734f5ed)

  • Emphasize embedding config is irreversible - add critical warnings (31971e3)

  • Emphasize guided config with all env vars always present (bee7f7d)

📦 Miscellaneous

  • Remove openssl-sys (598bd66)

  • Consolidate test commands and update package name to mo-memoria (#7) (7d94c6c)

  • Add mergify (#4) (b71f0fe)

🔧 Refactoring

  • Refactor all with rust (#33) (62a7076)

🚀 Features

  • Add installer script and improve release workflow (#37) (32fae53)

  • Lots of changes to api server and bug fixes (#29) (1b3d479)

  • Enhance with explain (#25) (07fed35)

  • Optimize MCP server startup and database configuration loading (#16) (e908548)

  • Enable offline mode for local embedding by default (#3) (d446a13)

  • L0/L1 tiered memory retrieval + redundancy compression + governance improvements (#2) (9d99085)

467 files · 445 not served here

Advantages

Limitations

Security

Risk level: Medium risk

This brain runs

Agent instructions that run or fetch something (41)

  • .cursor/rules/memory.mdc: If ⚠️ health warnings appear → inform the user and offer to run `memory_governance`.
  • .cursor/rules/memory.mdc: | Type | Use for | Examples | |------|---------|---------| | `semantic` | Project facts, technical decisions (default) | "Uses MatrixOne as primary DB", "API follows REST conventions" | | `profile` | User/agent identity and preferences | "Prefers concise answers", "Works on mo-dev-agen …[+460 chars]
  • .kiro/steering/memory-hygiene.md: Run `memory_governance` (1h cooldown) when you notice ANY of these:
  • .kiro/steering/memory-hygiene.md: Run `memory_consolidate` (30min cooldown) when:
  • .kiro/steering/memory.md: | Type | Use for | Examples | |------|---------|---------| | `semantic` | Project facts, technical decisions (default) | "Uses MatrixOne as primary DB", "API follows REST conventions" | | `profile` | User/agent identity and preferences | "Prefers concise answers", "Works on mo-dev-agen …[+460 chars]
  • .kiro/steering/session-lifecycle.md: Before your first response, run a multi-query bootstrap to load full context:
  • .kiro/steering/skills.md: | Skill | When to use | |-------|-------------| | [Architecture](../../skills/architecture/SKILL.md) | Navigating or modifying Memoria code | | [API Reference](../../skills/api-reference/SKILL.md) | Calling or implementing REST endpoints | | [Deployment](../../skills/deployment/SKILL.m …[+385 chars]
  • plugins/clawhub/thememoria/SKILL.md: Install or verify the OpenClaw plugin: `references/setup.md`
  • skills/api-reference/SKILL.md: It does not generate embeddings or run vector, graph, hybrid, temporal, or confidence scoring and is intentionally not exposed as an MCP tool.
  • skills/architecture/SKILL.md: async fn execute(&self, store, task, plan) -> Result<GovernanceExecution>;
  • skills/architecture/SKILL.md: make check # cargo check + clippy -D warnings (MUST pass)
  • skills/architecture/SKILL.md: make test-unit # Unit tests (no DB): memoria-core, memoria-service, memoria-mcp
  • skills/architecture/SKILL.md: make test # All tests (needs MatrixOne, --test-threads=1)
  • skills/architecture/SKILL.md: make test-e2e # API e2e tests only
  • skills/deployment/SKILL.md: docker compose up -d
  • skills/deployment/SKILL.md: Verify: `curl http://localhost:8100/health` · uses the network
  • skills/deployment/SKILL.md: Run behind reverse proxy with TLS in production
  • skills/local-embedding/SKILL.md: make build-local
  • skills/local-embedding/SKILL.md: | Problem | Fix | |---------|-----| | "compiled without local-embedding" | Build from source: `make build-local` | | Model download fails | Set `HF_ENDPOINT` for mirror, or manually download to `~/.cache/fastembed/` | | High memory | Default ~100MB.
  • skills/plugin-development/SKILL.md: "capabilities": ["governance.plan", "governance.execute"],
  • skills/plugin-development/SKILL.md: `capabilities`: must include `governance.plan` and/or `governance.execute`
  • skills/plugin-development/SKILL.md: if ctx["phase"] == "execute" {
  • skills/release/SKILL.md: | Step | Who | How | |------|-----|-----| | Bump version, tag, push | You | `make release VERSION=x.y.z` | | Build binaries (4 platforms) | CI | `release-rust.yml` | | Build + push Docker image | CI | `release-docker.yml` | | Create GitHub Release | CI | `softprops/action-gh-release` |
  • skills/release/SKILL.md: git status # Must be clean
  • skills/release/SKILL.md: make release VERSION=0.2.0
  • skills/release/SKILL.md: make release-rc VERSION=0.2.0-rc1
  • skills/release/SKILL.md: make release-docker # :latest
  • skills/release/SKILL.md: make release-docker VERSION=0.2.0 # :0.2.0 + :latest
  • skills/release/SKILL.md: Both release workflows run full test suite before publishing.
  • skills/release/SKILL.md: [ ] `make release VERSION=x.y.z`
  • skills/setup/SKILL.md: Ask: "Use Memoria Cloud, or run your own instance?"
  • skills/setup/SKILL.md: **Memoria Cloud (recommended)** → sign up at [thememoria.ai](https://thememoria.ai/auth), get API URL + token, then proceed to Step 2 · uses the network
  • skills/setup/SKILL.md: No → run `docker compose up -d` in the Memoria repo root (wait 30-60s for first start)
  • skills/setup/SKILL.md: One-line install (recommended):
  • skills/setup/SKILL.md: Or download manually from [GitHub Releases](https://github.com/matrixorigin/Memoria/releases). · uses the network
  • skills/setup/SKILL.md: Platform-specific manual install:
  • skills/setup/SKILL.md: docker compose up -d # Start MatrixOne
  • skills/setup/SKILL.md: docker ps --filter name=matrixone # Verify (wait 30-60s)
  • skills/setup/SKILL.md: Or run: `memoria status`
  • skills/setup/SKILL.md: | Problem | Fix | |---------|-----| | MatrixOne won't start | `docker logs memoria-matrixone` | | Port 6001 in use | Change `MO_PORT` in `.env` | | Can't connect to DB | Wait 30-60s on first start | | Docker permission denied | `sudo usermod -aG docker $USER && newgrp docker` | | Docke …[+152 chars]
  • skills/setup/SKILL.md: Run `which memoria` to verify CLI installed 2.

Install scripts (5)

  • README.md: curl -sSL https://raw.githubusercontent.com/matrixorigin/Memoria/main/scripts/install.sh | bash · uses the network
  • README.md: curl -sSL https://raw.githubusercontent.com/matrixorigin/Memoria/main/scripts/install.sh | bash · uses the network
  • README.md: command -v memoria >/dev/null || curl -sSL https://raw.githubusercontent.com/matrixorigin/Memoria/main/scripts/install.sh | bash -s -- -y -d ~/.local/bin · uses the network
  • scripts/install.ps1: pwsh scripts/install.ps1 · uses the network
  • scripts/install.sh: sh scripts/install.sh · uses the network
  • Medium risk: runs-install-script-remote-exec (README.md:155)
  • Medium risk: runs-install-script-remote-exec (README.md:175)
  • Medium risk: runs-install-script-remote-exec (README.md:194)
  • Medium risk: runs-install-script-network-variable-host (scripts/install.ps1)
  • Medium risk: network-variable-host (scripts/install.ps1:119)
  • Medium risk: network-variable-host (scripts/install.ps1:125)
  • Medium risk: runs-install-script-network-variable-host (scripts/install.sh)
  • Medium risk: network-variable-host (scripts/install.sh:295)
  • Medium risk: runs-instruction-instruction-network (skills/setup/SKILL.md:14)
  • Medium risk: remote-exec-pipe (skills/setup/SKILL.md:58)
  • Medium risk: runs-instruction-instruction-network (skills/setup/SKILL.md:61)
  • Low risk: scripts-present (scripts/install.ps1)
  • Low risk: scripts-present (scripts/install.sh)
  • Low risk: network-instructions (skills/deployment/SKILL.md:14)
  • Low risk: network-instructions (skills/setup/SKILL.md:58)

Attribution and licence

Created by
Matrix Origin
Publisher
Matrix Origin (Official Matrix Origin project)
Source
matrixorigin/memoria · commit 93ccccf
Licence
Apache License 2.0 (files served here)
  • ATTRIBUTION.md (written by AutoGineer)
Synced

AutoGineer is not affiliated with or endorsed by Matrix Origin.

Install from source

445 of its files are not served here, so there is no ZIP. matrixorigin/memoria at 93ccccf