Models & MCPPlugin

causal-memory

JingxuanC/causal-memory

causal-memory is a tool for DeepSeek Harness. Causal memory layer for AI agents — MCP server that records decision→outcome relationships. Survives compaction.

View repository

JingxuanC/causal-memory Screenshot preview

Stars: 49
Forks: 3
Issues: 10
Update: 57 days

REVIEW SCORECARD

Review Scorecard

7.8/10Average

License compliance9.0

Engineering quality6.5

Content completeness7.0

Repository scale7.0

Maintenance activity8.0

✓ No risk detected · Automated scan results are for reference only, not an official endorsement

AI DEEP REVIEW

Worth AI Review

7.2/10Consider

Promising causal-memory MCP server with strong benchmarks, but install instructions are missing and security details are

Code quality8

README cites 368 tests, a Rust workspace, versioned releases (v0.9.3), and reproducible demo/benchmark scripts, indicating solid engineering rigor.

Security6

No install command, permissions, or secret-handling details are provided, so risk cannot be assessed from the given information.

Utility8

Addresses a real, common pain point (agents forgetting why decisions were made across context compaction) with a measured 100% vs 45% compaction-survival advantage.

Maintenance8

Last updated 2026-08-26, not archived, with an active v0.9.3-alpha release and benchmark iterations (v12 to v13) showing ongoing development.

Documentation6

README is rich in benchmarks, demos, and architecture rationale, but the install command is listed as unknown and no setup/usage instructions are shown.

Generated by AI after reading the project README — a decision aid, not an endorsement. Neutral scores are given when information is limited.

PROJECT READMEREADMEExpandCollapse

Loading GitHub README...

PROJECT TOPICS

Project topics

agent-memory causal-inference deepseek-harness dsh dsh-plugin llm-agents long-term-memory mcp mcp-server rust

VALIDATION LADDER

Validation progress

Structure check pending

01Store discoveryPassed

02ClassificationPassed

03Structure checkPending

04Sandbox validationPending

FAQ

Frequently Asked Questions

What is causal-memory used for?

Causal memory layer for AI agents — MCP server that records decision→outcome relationships. Survives compaction.

How popular is causal-memory?

causal-memory has 49 stars and 3 forks on GitHub, last updated 2026-08-26.

What license does causal-memory use?

causal-memory is distributed under the Apache-2.0 license.

Is causal-memory compatible with DeepSeek Harness?

causal-memory is listed in the DSH Universe directory as a tool for DeepSeek Harness. This plugin is listed in the DSH Universe directory and covered by its validation pipeline.

CLASSIFICATION EVIDENCE

Classification evidence

Project typePlugin

Feature categoryModels & MCP

Rule confidenceHigh

The system checks GitHub Topics against the site taxonomy and keyword rules. Current matches:agent-memory、causal-inference、long-term-memory、mcp、mcp-server。

causal-memory

Review Scorecard

Worth AI Review

Project topics

Validation progress

Frequently Asked Questions

Classification evidence

Related projects

dsh-purge

AI-Novel-Writer

agentrq

awesome-ai-plugins

sandbase-harness

dsh-desktop