Evolve
Plugin for DeepSeek Harness
Repository ownerchenzheshushi-commitsdsh-evolve
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.
How to install
dsh plugin --profile web add github:chenzheshushi-commits/dsh-evolveSuggested commands are derived from the catalog record. Review the repository README, requested permissions, and source before installation. Read the full guide.
What this plugin does
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.
Repository README
View on GitHubThis content is loaded directly from the repository HEAD and rendered safely in your browser. It is maintained by the repository author and is not verified or endorsed by this directory.
Repository and source evidence
This public repository was verified through the GitHub API. The catalog source links the plugin to this repository, but directory inclusion is not an official endorsement.
- Repository owner
- chenzheshushi-commits
- Author
- No independently verified author field is available
- Source
- https://github.com/topics/dsh-plugin
Example configuration
Use the repository README and manifests for plugin-specific configuration. This command inspects the active profile.
dsh --profile web --dump-configSupported DeepSeek Harness versions
No explicit DSH version range in catalog evidence
No verifiable DSH version range is available; test before installation.
Environment, permissions, and dependencies
Environment
Primary language: JavaScript; runtime version not verified.
Permissions
Permissions are unverified; review the README, environment variables, and external access.
Dependencies
Dependencies are unverified; use the repository manifest and lockfile.
GitHub metadata
- Stars / forks
- 4 / 0
- Last repository update
- August 24, 2026
- Latest release
- v0.4.2 · August 24, 2026
- License
- MIT
- Default branch
- main
- Available / archived
- Publicly reachable and not archived
Installation safety
Third-party plugins can execute code in Harness. Review source, dependencies, build scripts, and permissions, then test in isolation.
Git installs may run prepare/build scripts outside the sandbox; trust the source and pin a commit.
Read the plugin safety guideCommon errors and troubleshooting
No plugin-specific troubleshooting was collected; these are general checks.
- 1. Plugin missing after installation
Confirm installation and launch use the same profile, then run dsh --profile web --dump-config to check whether the bundle entered the composed configuration.
- 2. Git dependency build is blocked
pnpm 10+ may block prepare scripts. Only after reviewing the source, add the exact package key reported by pnpm to allowBuilds, then retry.
- 3. Version or configuration mismatch
Check the repository README, releases, and compatibility evidence. Do not treat directory-wide commands as promises from the plugin author.
Security
More plugins in this category
Mirage
strukto-ai / mirage
The World's First Unified Virtual Filesystem For AI Agents
Aegis
GanyuanRan / Aegis
Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across long tasks.
Api Relay Audit
toby-bridges / api-relay-audit
Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewriting, SSE anomalies, error leakage, and Web3 wallet risks.
K8e
xiaods / k8e
k8e.sh - OpenSource Agentic AI Sandbox Matrix
Hol Guard
hashgraph-online / hol-guard
Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.
Anolisa
alibaba / anolisa
ANOLISA (Agentic Nexus Operating Layer & Interface System Architecture) | Agentic OS with runtime, security, observability, and Tokenless response compression for lower token usage and cost.
DeepSec
Unclecheng-li / DeepSec
DeepSec — AI Security Offense & Defense Platform. Shield audits AI-generated code for hallucinated packages, missing safeguards & AI pattern errors in real time. Spear automates authorized penetration testing with 40+ skill packs, from recon to PoC.
Auto Mode
NanmiCoder / dsh-auto-mode
Safe automatic permissions for DeepSeek Harness.