causal-memory
★ 99
vs
sqlite-memory-mcp
★ 18
causal-memory vs sqlite-memory-mcp
causal-memory: Causal-memory is an agent memory system with a causal core, uniquely modeling both excitatory and inhibitory connections for robust long-term retention. It enables agents to understand not just what happened, but why it worked or failed, and anticipate outcomes, thereby preventing repeated mistakes.; sqlite-memory-mcp: SQLite Memory MCP Server provides a governed, local-first cross-agent memory solution for coding agents, built on SQLite. It features provenance-rich knowledge graphs, hybrid retrieval, and reviewable promotion workflows for robust, shared context across multiple AI agents.
01
TL;DR
causal-memoryMemory & Context · ★ 99
Preventing Repeated Mistakes: Agents can recall past `decision → outcome` causal edges, avoiding re-fixing the same bug or repeating past failed architectural choices.
sqlite-memory-mcpMemory & Context · ★ 18
Providing governed, shared memory for AI coding agents and LLMs to collaborate effectively on complex projects.
02
Side-by-Side Comparison
Field
causal-memorysqlite-memory-mcpCategory
Memory & Context
Memory & Context
Stars
★ 99
★ 18
License
Apache-2.0
MIT
Install Command
git clone https://github.com/JingxuanC/causal-memory.git && cd causal-memory && cargo build --release
git clone https://github.com/RMANOV/sqlite-memory-mcp.git && cd sqlite-memory-mcp && pip install -e .
Updated
1w ago
6d ago
Open Source
Yes
Yes
Tags
Agent Memory, Causal Reasoning, Long-term Memory
SQLite, Agent Memory, Knowledge Graph
03
Features
causal-memory01Causal Core with Excitatory and Inhibitory Connections: Models 'caused', 'enabled', and 'prevented' relationships using typed causal semantics and negative activation spread (GABA analogue).
02Immutable Consolidation & Q-value Dynamics: Employs hippocampus-style SWR (Sleep-Wake Replay) consolidation with LTP/LTD/GC, Q-value dynamics, and novelty-entropy triggers for robust memory evolution.
03Intervention & Counterfactual Query: Enables forward simulation to predict outcomes before action and contrastive analysis to compare outcomes of different alternatives.
04Compaction Survival: Stores causal information in an external SQLite database, making it immune to context window compaction and preserving critical 'why' knowledge.
05Unified Memory Graph: Integrates facts, temporal state, and decision-outcome causal edges into a single graph, accessible via RRF-fused retrieval (BM25 + semantic).
sqlite-memory-mcp01WAL mode for 10+ concurrent sessions without file locking conflicts, ensuring high availability and performance.
02Hybrid retrieval combining BM25/FTS5 keyword search with optional semantic (sqlite-vec) results using Reciprocal Rank Fusion.
03Provenance tracking and approval-aware promotion of candidate claims to canonical facts through a human or policy-gated review process.
04Cross-machine synchronization of shared entities across multiple devices via a private Git repository for consistent knowledge across workflows.
05Built-in structured task management functionality, including Kanban board generation, and session tracking for context continuity across restarts.
04
Use Cases
causal-memory↳Preventing Repeated Mistakes: Agents can recall past `decision → outcome` causal edges, avoiding re-fixing the same bug or repeating past failed architectural choices.
↳Proactive Warning and Intervention: Before committing risky actions (e.g., `git push --no-verify`), the system can fire DANGER warnings based on recorded past negative outcomes.
↳Root Cause Analysis: Trace multi-hop backward causal chains to identify the ultimate root cause of failures or unexpected outcomes.
↳Informed Decision Making: Agents can perform counterfactual comparisons between alternative actions, leveraging known outcomes to choose the best path.
↳Cross-Task Lesson Transfer: Discover and apply meta-edges (e.g., `similar_to`, `repeated`) to transfer lessons and patterns across different tasks or sessions.
sqlite-memory-mcp↳Providing governed, shared memory for AI coding agents and LLMs to collaborate effectively on complex projects.
↳Deploying agent memory solutions in privacy-first, offline, or embedded environments, including highly regulated sectors (e.g., finance, healthcare).
↳Coordinating complex, multi-agent workflows (e.g., conductor, executor, devil's advocate) with explicit debate protocols and knowledge consolidation.
↳Local-first knowledge management for individual developers or small teams needing zero-configuration data persistence and fast search capabilities.
FAQ
FAQ
What is the difference between causal-memory and sqlite-memory-mcp?
Both causal-memory and sqlite-memory-mcp are in the Memory & Context category. causal-memory has 99 stars, while sqlite-memory-mcp has 18 stars.
Which is better, causal-memory or sqlite-memory-mcp?
The best choice depends on your use case. Choose causal-memory if Preventing Repeated Mistakes: Agents can recall past `decision → outcome` causal edges, avoiding re-fixing the same bug or repeating past failed architectural choices., and sqlite-memory-mcp if Providing governed, shared memory for AI coding agents and LLMs to collaborate effectively on complex projects..
Is causal-memory free or open source?
Yes, causal-memory is open source on GitHub (Apache-2.0).
Is sqlite-memory-mcp free or open source?
Yes, sqlite-memory-mcp is open source on GitHub (MIT).
Cloud Infrastructure
AdDeploy on DigitalOcean
Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.
→