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
unified-agent-memory
Noelune/unified-agent-memory
unified-agent-memory is a tool for DeepSeek Harness. Unified fleet-wide agent memory system for DeepSeek Harness — shared Obsidian Vault for dsh, Codex, Claude Code & Hermes with dependency-free Python FTS5 core.
- Stars
- 5
- Forks
- 0
- Issues
- 1
- Update
- 48 days
REVIEW SCORECARD
Review Scorecard
7.5/10Average
License compliance9.0
Engineering quality5.4
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
7.4/10Consider
Ambitious multi-agent memory layer with a zero-dependency Python core and Obsidian-native storage, but unverified tests
Code quality7
README claims a stdlib-only Python core with SQLite FTS5, atomic file locks, and a layered core/adapter split documented in docs/DSH-MEMORY-ADAPTERS.md, but no test suite, CI config, or repo file tree is shown to verify engineering rigor.
Security7
README describes credential redaction, <memory-data> prompt-injection isolation tags, and 0600 secrets.yaml for the optional SiliconFlow API key, which are positive signals, but the embedding feature sends memory content to a third-party API and no independent audit is visible.
Utility8
Addresses a genuine pain point by letting dsh, Codex, Claude Code, and Hermes share one Markdown knowledge base with lifecycle features like promotion, adjudication, supersession, and decay-based forgetting.
Maintenance7
Last updated 2026-08-15, not archived, MIT-licensed, and the README shows an actively evolving feature set (hybrid retrieval, embeddings, session digest), though only 5 stars means limited community validation.
Documentation8
README is extensive with architecture diagrams, a feature matrix, vault layout, and an agent-driven deployment guide, but it is largely in Chinese and the install path depends on an agent reading docs/AGENT-DEPLOY.md rather than a plain manual setup.
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 dsh-unified-agent-memoryThis 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 unified-agent-memory used for?
Unified fleet-wide agent memory system for DeepSeek Harness — shared Obsidian Vault for dsh, Codex, Claude Code & Hermes with dependency-free Python FTS5 core.
How popular is unified-agent-memory?
unified-agent-memory has 5 stars and 0 forks on GitHub, last updated 2026-08-15.
What license does unified-agent-memory use?
unified-agent-memory is distributed under the MIT license.
Is unified-agent-memory compatible with DeepSeek Harness?
unified-agent-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 categoryAgents & sessions
Rule confidenceHigh
The system checks GitHub Topics against the site taxonomy and keyword rules. Current matches:agent-memory、claude-code、multi-agent、sqlite-fts5。
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