AgentIndex icon
AgentIndex
ContextGraph logo
ContextGraph
★ 22
vs
AgentRecall-MCP logo
AgentRecall-MCP
★ 371

ContextGraph vs AgentRecall-MCP

ContextGraph: ContextGraph is the knowledge layer in the AI agent infrastructure stack. It turns raw agent memories into searchable, governed, tradeable knowledge. It provides a shared memory bus with provenance, impact classification, and multi-protocol support including MCP, A2A, UCP, and real-time streaming.; 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

ContextGraph logo
ContextGraphRAG / Knowledge Base · ★ 22

Same-company agent follow with provenance and quorum building

Read ContextGraph 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
ContextGraph logoContextGraph
AgentRecall-MCP logoAgentRecall-MCP
Category
RAG / Knowledge Base
Memory & Context
Stars
★ 22
★ 371
License
MIT
MIT
Install Command
git clone https://github.com/AllenMaxi/ContextGraph.git && cd ContextGraph && python3 -m venv .venv && source .venv/bin/activate && pip install -e ".[server,mcp,dev]"
claude mcp add --scope user agent-recall -- npx -y agent-recall-mcp
Updated
6mo ago
1w ago
Open Source
Yes
Yes
Website
↗ Visit
↗ Visit
GitHub
↗ GitHub
↗ GitHub
Tags
agent-memory, agentic-rag, ai-agents
agent-memory, ai-agents, claude-code
03

Features

ContextGraph logoContextGraph
01Provenance Chains with immutable audit trails
02Impact Classification & Quorum Consensus for high-impact claims
03Pattern Subscriptions for graph-native knowledge monitoring
04GitHub-like Dashboard with agent profiles and knowledge browser
05Multi-protocol support (MCP, A2A, UCP) and real-time SSE streaming
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

ContextGraph logoContextGraph
↳Same-company agent follow with provenance and quorum building
↳Cross-company paid knowledge marketplace with impact-based pricing
↳Entity-aware pattern subscriptions for targeted alerts
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 ContextGraph and AgentRecall-MCP?
Both ContextGraph and AgentRecall-MCP are in the RAG / Knowledge Base category. ContextGraph has 22 stars, while AgentRecall-MCP has 371 stars.
Which is better, ContextGraph or AgentRecall-MCP?
The best choice depends on your use case. Choose ContextGraph if Same-company agent follow with provenance and quorum building, and AgentRecall-MCP if Maintain context across AI agent sessions (Claude Code, Cursor, etc.).
Is ContextGraph free or open source?
Yes, ContextGraph is open source on GitHub (MIT).
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 ContextGraph →Alternatives to AgentRecall-MCP →ContextGraph details →AgentRecall-MCP details →