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.
GITHUB TOPIC
13projects include this topic
The "self-evolving" topic on GitHub groups 13 open-source projects in the DeepSeek Harness (DSH) ecosystem, led by MemOS with 11k GitHub stars. MemOS — Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35. Every project here is indexed by DSH Universe with live GitHub data — stars, activity and install status — so you can compare and install directly.
{count} projects
Exact GitHub Topic match
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.
huytieu
Self-evolving second brain with 33 AI skills, 10 agents, and people CRM. Closed-loop harness: a V-model verification lifecycle where the worker never grades its own homework. Plus paired anti-slop design skills for marketing and product UI. Works with Claude Code, Cursor, Kiro, Gemini CLI, Codex.
Karbo123
Self-evolving research workflow
chenzheshushi-commits
Self-evolving memory + skill lifecycle for DeepSeek Harness — durable cross-session memory with zero-token deterministic recall, tiered approval, reinforcement learning from repetition, and anti-bloat convergence for both skills and memory.
timwhitez
Evidence-first, crash-resumable self-evolution engine for DeepSeek Harness and Harbor.
beijingwahw
DSH Proactive — proactive intelligence scheduling plugin: autonomous heartbeat + scientist/theorist dual minds (Bayesian experiment design and law induction) + energy symbiosis economy + curiosity exploration + safety governance, Raft consensus and hot updates
huchunlinnk
Recursive Self-Improvement engine for DeepSeek Harness — DSH maintains DSH: bounded perceive→integrate→verify→parity→repair→propose loop enforcing 1:1 upstream feature parity
lispking
A self-evolving plugin for DeepSeek Harness (dsh). It observes how the agent runs, proposes improvements to its own assets via the LLM, validates each proposal inside a sandboxed trial agent, and applies only verified mutations — with a versioned ledger and automatic rollback on regression.
3likofj
该插件是 DSH 上的可编程记忆编排层 + 自我进化引擎
findshan
Self-evolving memory for DeepSeek Harness: capture → dream consolidation → retrieval injection → evolve. User profile, project memory, correction learning, resume narrative — with provenance back to the replayable session log. Self-evolving memory plugin.
JayDong9130
Proof-carrying Skill self-evolution for DeepSeek Harness
Bear0117
Recursive Harness for DeepSeek Harness (dsh): Propose, Probe, Compose loops and a cross-task experience library (Harness², arXiv:2610.14224). Work in progress.
EvoMap
Evolver for DeepSeek Harness, by EvoMap: a harness that gets smarter the more you use it. Recalls a proven strategy before each prompt, grades it on evidence (checks run, edits kept, your next reply), and reports back to the EvoMap network so what works gets reused and what fails sinks.