AgentIndex icon
AgentIndex
Co-Engram logo
Co-Engram
★ 11
vs
ditto logo
ditto
★ 298

Co-Engram vs ditto

Co-Engram: 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.; ditto: Ditto is a tool that analyzes your past AI agent coding sessions to automatically create a personalized working profile. This profile helps AI agents understand your specific work habits, design preferences, and writing style, making them act more like you.

01

TL;DR

Co-Engram logo
Co-EngramMemory & Context · ★ 11

AI agent knowledge base: Agents can automatically capture, search, and update team knowledge through natural conversation.

Read Co-Engram full review →
ditto logo
dittoMemory & Context · ★ 298

Customize AI agents to understand your definition of 'done,' preferred debugging methods, and UI design principles.

Read ditto full review →
02

Side-by-Side Comparison

Field
Co-Engram logoCo-Engram
ditto logoditto
Category
Memory & Context
Memory & Context
Stars
★ 11
★ 298
License
MIT
MIT
Install Command
npm install -g @co-engram/claude-code && mkdir -p ~/team-memory && cd ~/team-memory && git init && co-engram config data-root $HOME/team-memory
npx skills add ohad6k/ditto@ditto
Updated
2mo ago
1w ago
Open Source
Yes
Yes
Website
↗ Visit
↗ Visit
GitHub
↗ GitHub
↗ GitHub
Tags
AI Memory System, Self-Evolving, Knowledge Management
AI Agents, Personalization, Context Management
03

Features

Co-Engram logoCo-Engram
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.
ditto logoditto
01Mines real coding-agent session logs (e.g., Claude Code, Codex, Copilot CLI) to extract implicit user behaviors.
02Generates a private, local working profile (`you.md`) that AI agents read before every task.
03Distinguishes and loads separate layers for work, design, and writing profiles based on the task.
04Ensures privacy by processing logs locally with best-effort redaction of secrets.
05Renders a shareable 'profile card' summarizing key laws and traits.
04

Use Cases

Co-Engram logoCo-Engram
↳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.
ditto logoditto
↳Customize AI agents to understand your definition of 'done,' preferred debugging methods, and UI design principles.
↳Improve agent communication to match your actual working voice and avoid repetitive explanations.
↳Enhance agent rejections to align with what you typically reject on sight (e.g., 'fix the one thing,' not rewriting).
↳Develop a consistent persona for multi-agent systems without explicitly writing down all rules.
FAQ

FAQ

What is the difference between Co-Engram and ditto?
Both Co-Engram and ditto are in the Memory & Context category. Co-Engram has 11 stars, while ditto has 298 stars.
Which is better, Co-Engram or ditto?
The best choice depends on your use case. Choose Co-Engram if AI agent knowledge base: Agents can automatically capture, search, and update team knowledge through natural conversation., and ditto if Customize AI agents to understand your definition of 'done,' preferred debugging methods, and UI design principles..
Is Co-Engram free or open source?
Yes, Co-Engram is open source on GitHub (MIT).
Is ditto free or open source?
Yes, ditto is open source on GitHub (MIT).
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
→

Related

Alternatives to Co-Engram →Alternatives to ditto →Co-Engram details →ditto details →