AgentIndex icon
AgentIndex
ctx-open logo
ctx-open
★ 59
vs
AgentRecall-MCP logo
AgentRecall-MCP
★ 371

ctx-open vs AgentRecall-MCP

ctx-open: CTX is a cognitive version control system for AI agents, preserving structured reasoning artifacts as durable state instead of ephemeral chat transcripts. It enables agents to maintain continuity across sessions, track decisions, and reproduce reasoning paths. The system includes a CLI, a local MCP server, and a web viewer.; AgentRecall-MCP: AgentRecall is a learning loop for AI agents that provides persistent, compounding memory. It captures corrections automatically, surfaces past insights across projects, and uses a five-layer memory pyramid with Ebbinghaus decay and Bayesian feedback. Zero cloud, all local markdown files.

01

TL;DR

ctx-open logo
ctx-openMemory & Context · ★ 59

Multi-session agent continuity: resume work across interruptions without re-investigation

Read ctx-open full review →
AgentRecall-MCP logo
AgentRecall-MCPMemory & Context · ★ 371

Maintain context across AI agent sessions (Claude Code, Cursor, etc.)

Read AgentRecall-MCP full review →
02

Side-by-Side Comparison

Field
ctx-open logoctx-open
AgentRecall-MCP logoAgentRecall-MCP
Category
Memory & Context
Memory & Context
Stars
★ 59
★ 371
License
NOASSERTION
MIT
Install Command
git clone https://github.com/diegoxtr/ctx-open.git && cd ctx-open && bash ./install.sh
claude mcp add --scope user agent-recall -- npx -y agent-recall-mcp
Updated
1mo ago
1w ago
Open Source
Yes
Yes
Website
↗ Visit
↗ Visit
GitHub
↗ GitHub
↗ GitHub
Tags
agent-memory, ai, ai-agents
agent-memory, ai-agents, claude-code
03

Features

ctx-open logoctx-open
01Structured cognitive versioning with goals, tasks, hypotheses, evidence, decisions, and conclusions
02Persistent working memory that survives model changes, provider changes, and session loss
03Local stdio MCP server for integration with MCP-capable agents and IDEs
04Cross-platform CLI and web viewer supporting multiple repositories and branches
05Agent operating protocol with minimal state machine: working context, closeout, commit
AgentRecall-MCP logoAgentRecall-MCP
01Persistent, compounding memory with 200-line awareness cap
02Automatic correction capture and alignment checking
03Cross-project insight recall via keyword and semantic (pgvector) search
04Zero cloud, all local markdown files, Obsidian-compatible
0510 MCP tools for agents, plus SDK and CLI
04

Use Cases

ctx-open logoctx-open
↳Multi-session agent continuity: resume work across interruptions without re-investigation
↳Tracking and explaining AI decisions: preserve the reasoning trail for auditing and reproducibility
↳Generating structured training data: capture how ideas evolved with complete evidence and decisions
AgentRecall-MCP logoAgentRecall-MCP
↳Maintain context across AI agent sessions (Claude Code, Cursor, etc.)
↳Capture and learn from user corrections in software development
↳Coordinate memory across multiple parallel agents
FAQ

FAQ

What is the difference between ctx-open and AgentRecall-MCP?
Both ctx-open and AgentRecall-MCP are in the Memory & Context category. ctx-open has 59 stars, while AgentRecall-MCP has 371 stars.
Which is better, ctx-open or AgentRecall-MCP?
The best choice depends on your use case. Choose ctx-open if Multi-session agent continuity: resume work across interruptions without re-investigation, and AgentRecall-MCP if Maintain context across AI agent sessions (Claude Code, Cursor, etc.).
Is ctx-open free or open source?
Yes, ctx-open is open source on GitHub (NOASSERTION).
Is AgentRecall-MCP free or open source?
Yes, AgentRecall-MCP 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 ctx-open →Alternatives to AgentRecall-MCP →ctx-open details →AgentRecall-MCP details →