Agents & sessionsSkill
EverOS
EverMind-AI
One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
Structure check pending
agent-memoryagentic-aiaichats
Back to Marketplace
Agents & sessionsPlugin
GraphFlow
Roarpeng/GraphFlow
GraphFlow is a tool for DeepSeek Harness. Local-first code knowledge graph and context harness for coding agents. MCP + DeepSeek Harness (dsh) plugin.
- Stars
- 14
- Forks
- 1
- Issues
- 0
- Update
- 4 days
REVIEW SCORECARD
Review Scorecard
8.1/10Good
License compliance9.0
Engineering quality6.2
Content completeness8.0
Repository scale7.0
Maintenance activity9.0
✓ No risk detected · Automated scan results are for reference only, not an official endorsement
AI DEEP REVIEW
Worth AI Review
8.0/10Recommended
Well-documented, actively maintained local-first context harness with reproducible benchmarks and offline operation; wor
Code quality8
README cites a 132-query golden retrieval set running in CI, commit-anchored benchmark JSON dumps, and a one-command offline reproduction script (`npm run proof:flywheel`), indicating real test and CI infrastructure.
Security7
Runs fully offline with no API key required and the README documents memory-poisoning protections (provenance markers, canary validation, isolated anti-patterns), though the NOASSERTION license and lack of visible permission details keep this from a higher score.
Utility9
Addresses a genuine pain point for long-running coding agents by combining a 12-language AST code graph, token-budgeted context compression, and cross-session learning, exposed portably over MCP to 15+ agents.
Maintenance8
Last updated 2026-08-23 with an active npm release (1.18.1), a published ROADMAP, and an open invitation for independent benchmark reproduction, indicating ongoing development.
Documentation8
README provides a clear install command, quick-start CLI examples, MCP config JSON, benchmark methodology links, and a Chinese translation, though the excerpt is truncated mid-table.
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...
The GitHub README is temporarily unavailable. Please try again later.
Open repositoryINSTALL REFERENCE
Install reference
dsh plugin --profile web add @roarpeng/graphflowThis command passed the install-plan safety checks and can be executed by the DSH host. Validation is not a security audit or official endorsement.
PROJECT TOPICS
Project topics
VALIDATION LADDER
Validation progress
01Store discoveryPassed
02ClassificationPassed
03Structure checkPending
04Sandbox validationPending
FAQ
Frequently Asked Questions
What is GraphFlow used for?
Local-first code knowledge graph and context harness for coding agents. MCP + DeepSeek Harness (dsh) plugin.
How popular is GraphFlow?
GraphFlow has 14 stars and 1 forks on GitHub, last updated 2026-09-29.
What license does GraphFlow use?
GraphFlow is distributed under the Apache-2.0 license.
Is GraphFlow compatible with DeepSeek Harness?
GraphFlow 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 categoryAgents & sessions
Rule confidenceHigh
The system checks GitHub Topics against the site taxonomy and keyword rules. Current matches:context-engine、mcp、multi-agent。
Agents & sessionsSkill
MemOS
MemTensor
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.
Structure check pending
agentagentic-aiaiai-agents
Agents & sessionsPlugin
harnessrouter
HarnessRouter
HarnessRouter Community Edition: the self-hosted, Apache-2.0 edition of the unified interface for agent harnesses. Run Codex, Claude Code, Hermes, PI, DSH, and more through one API, with sessions, streaming, files, cancellation, and failure handling. Implements the Unified Harness Protocol (UHP), an open standard. Your keys, your infrastructure.
Structure check pending
agent-apiagent-frameworkagent-harnessai-agents
Agents & sessionsSkill
memsearch
zilliztech
A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.
Structure check pending
agentagent-memoryai-agentsclaude-code
Agents & sessionsPlugin
Tianshu-harness
huiliyi37
Tianshu is a terminal coding agent runtime built on the harness project (Tui X Gui), with prefix-cache engineering optimization for DeepSeek V4 (measured steady-state hit rate of 97–99% in long sessions) and deep adaptation. It breaks out of the traditional AI coding assistant's limit of treating the LLM merely as a tool, and is built on a cognitive virtual machine (CVM), a self-awareness layer and Stigmergy self-decaying memory, making the AI a development partner with independent judgment and cognitive safeguards.
Structure check pending
ai-agentcoding-agentcontext-managementdeepseek
Agents & sessionsPlugin
graph-memory
adoresever
Deepseek Harness, Openclaw knowledge graph memory plugin. Invited to present at Tsinghua University seminar in April 2026. Knowledge Graph + Memory；Knowledge Graph Context Engine for OpenClaw — extracts structured triples from conversations, compresses context 75%, enables cross-session experience reuse
Structure check pending
claude-codecodexdeepseekdeepseek-harness