AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompare
Home/
Memory & Context/
Co-Engram
Co-Engram logo

Co-Engram

Active·★ 11·MIT·Updated 2026-08-22

Co-Engram is an advanced, self-evolving memory system designed for AI agents and teams, which models memory after the human brain's plasticity. It allows memories to strengthen with use, weaken upon failure, consolidate, and verify themselves, all stored as plain Markdown in Git for transparent version control.

#AI Memory System#Self-Evolving#Knowledge Management#AI Agents#RAG#Git-based Storage#Metacognition
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.

Guides
#Long-Term Memory
$ Install
$ npm install -g @co-engram/claude-code && mkdir -p ~/team-memory && cd ~/team-memory && git init && co-engram config data-root $HOME/team-memory
↗ Visit site★ GitHub
01

Features

01Self-maintaining memory: An engine automatically strengthens, consolidates, and refutes memories based on usage and feedback.
02Git-based storage with Stable IDs: Memories are stored as Markdown files in Git with stable ULIDs, allowing clean diffs and persistent references.
03Tiered disclosure for LLM context: Provides different tiers of memory detail (catalog, digest, content) to optimize LLM context window usage.
04Learning loop & plasticity: Memories strengthen with successful use (LTP) and decay with failures or disuse (LTD), similar to brain plasticity.
05Synapse graph for related context: Connects memories with typed synapses, allowing automatic traversal to retrieve related context during search.
02

Compatibility

Claude Code
Host AI
Verified via docs
OpenClaw
Host AI
Verified via docs
TypeScript
Core Language
Verified via docs
Git
Data Backend
Verified via docs
Obsidian
Integration
Verified via docs
Node.js
Runtime
Verified via docs
03

Quick start

1
$ npm install -g @co-engram/claude-code
2
$ mkdir -p ~/team-memory
3
$ cd ~/team-memory
4
$ git init
5
$ co-engram config data-root $HOME/team-memory
04

Use cases

↳AI agent knowledge base: Agents can automatically capture, search, and update team knowledge through natural conversation.
↳Team decision memory: Store important decisions and their rationale, which get reinforced when proven effective.
↳Procedural knowledge (Skills): Capture workflows, checklists, and operational capabilities that agents can learn, invoke, and chain.
↳Collaborative memory for developers: Maintain a shared, self-evolving knowledge base for coding patterns, system configurations, and project details.
↳Onboarding new team members: Provide new team members with a living, self-curating memory system that quickly surfaces relevant information.
05

Alternatives

⚡Top VS:
VSenquire-mcp★34→VSmemora★744→VSborhan★39→VS

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Compatibility03Quick start04Use cases05Alternatives
okf-agent-memory
★830
→
enquire-mcp logo
enquire-mcp★ 34
The most advanced Obsidian MCP — long-term memory for AI agents. Hybrid retrieval (BM25 + ML + BGE rerank, RRF-fused), HNSW live-update, agentic RAG (HyDE + sub-question), Obsidian Bases, PDFs+OCR. For Claude Code/Desktop, Cursor, ChatGPT, Codex, OpenClaw. MCP-native, MIT, SLSA L2.
VSCompare→
memora logo
memora★ 744
Give your AI agents persistent memory.
VSCompare→
borhan logo
borhan★ 39
Save conversations, search by idea, read the surrounding context. Memory for AI agents.
VSCompare→
okf-agent-memory logo
okf-agent-memory★ 830
Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.
VSCompare→
pipeshub-ai logo
pipeshub-ai★ 3.8k
The open-source context layer for AI agents. PipesHub turns your company's knowledge (Slack, Drive, Jira, GitHub, Microsoft 365 and 40+ connectors) into a permission-aware workspace that agents can search, grep, navigate and cite. MCP, SDKs and built-in agents. Self-hosted.
VSCompare→
dakera-deploy logo
dakera-deploy★ 19
Self-hosted Dakera AI memory server — Docker Compose, Kubernetes, Helm, HA cluster setup, and monitoring.
VSCompare→
hippo-memory logo
hippo-memory★ 784
Biologically-inspired memory for AI agents. Decay, retrieval strengthening, consolidation. Zero runtime deps, SQLite, MCP. Benchmarked retrieval with an opt-in hosted TypeSafe Jev reranker.
VSCompare→
ditto logo
ditto★ 298
Mine your Claude Code and Codex logs into a local you.md agent profile.
VSCompare→
See all alternatives →
Co-Engram /
Co-Engram
↗

Self-evolving team memory

11MIT
Last commit2mo ago
StatusActive
CategoryMemory & Context
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit