Agent äžäŒè¯æèœ
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.
åŸ
ç»ææ£æ¥
agent-memoryagentic-aiaichats
è¿åæ件åžåº
Agent äžäŒè¯æèœ
soya
soyoungzsy/soya
soya is a tool for DeepSeek Harness. ð³ SOYA Personal Board â your private board of directors: 12 great minds from history for decisions, morning meetings & card vault. DeepSeek Harness preset + portable skills. Personal board: let wise minds from past and present form your private wisdom brain.
- Stars
- 4
- Forks
- 0
- Issues
- 0
- Update
- 27 days
REVIEW SCORECARD
è¯æµæ绩å
6.9/10Average
detail.dimSecurity6.0
detail.dimQuality5.4
detail.dimContent7.0
detail.dimDeps7.0
detail.dimMaintenance9.0
â æ Riskyæ£åº · èªåšåæ«æç»æä» äŸåèïŒéå®æ¹è乊
AI DEEP REVIEW
AI 深床è¯æµ
6.2/10Consider
A conceptually rich personal-board preset with portable skills, but install steps and engineering details are undocument
Code quality6
The README excerpt shows only a member-card template and references docs/customize-your-board.md, with no tests, CI, or project structure visible, so engineering rigor cannot be assessed.
Security6
No install command, download source, or permission model is provided, so risk cannot be evaluated from the given information.
Utility7
It targets a real and common need for structured decision-making and self-management by packaging 12 historical thinkers as reusable agent skills.
Maintenance7
The repository is not archived and was last updated 2026-08-20, indicating recent activity, though only 4 stars suggest a small user base.
Docs5
The README excerpt is a blank member-card template rather than installation or usage instructions, and the install command is listed as unknown, leaving onboarding unclear.
Generated by AI after reading the project README, as a decision aid; neutral scores are given when information is thin. Not an official endorsement.
PROJECT README项ç®è¯Žæå±åŒCollapse
æ£åšè¯»å GitHub README...
README ææ¶æ æ³è¯»åã
ååŸä»åºPROJECT TOPICS
项ç®æ çŸ
VALIDATION LADDER
éªè¯è¿åºŠ
01åžåºåç°Passed
02åœç±»è¯å«Passed
03ç»ææ£æ¥Pending
04å®æºéªè¯Pending
FAQ
Frequently Asked Questions
What is soya used for?
ð³ SOYA Personal Board â your private board of directors: 12 great minds from history for decisions, morning meetings & card vault. DeepSeek Harness preset + portable skills. Personal board: let wise minds from past and
How popular is soya?
soya has 4 stars and 0 forks on GitHub, last updated 2026-08-20.
Is soya compatible with DeepSeek Harness?
soya 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
/10ç±»äŸæ®
项ç®ç±»åæèœ
åèœ/10ç±»Agent äžäŒè¯
è§å眮信床High
System reads GitHub Topics first, then compares against the in-site category dictionary and word-root rules. Current match:agent-skillsãpersonal-developmentã
Agent äžäŒè¯æèœ
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.
åŸ
ç»ææ£æ¥
agentagentic-aiaiai-agents
Agent äžäŒè¯æèœ
memsearch
zilliztech
A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.
åŸ
ç»ææ£æ¥
agentagent-memoryai-agentsclaude-code
Agent äžäŒè¯æ件
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.
åŸ
ç»ææ£æ¥
agent-apiagent-frameworkagent-harnessai-agents
Agent äžäŒè¯æ件
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 97â99% 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.
åŸ
ç»ææ£æ¥
ai-agentcoding-agentcontext-managementdeepseek
Agent äžäŒè¯æ件
graph-memory
adoresever
Deepseek Harness, Openclaw knowledge graph memory plugin. Invited to present at Tsinghua University seminar in April 2026. Knowledge Graph + MemoryïŒKnowledge Graph Context Engine for OpenClaw â extracts structured triples from conversations, compresses context 75%, enables cross-session experience reuse
åŸ
ç»ææ£æ¥
claude-codecodexdeepseekdeepseek-harness