v0.51.57 · MIT
Local-first, agent-native control plane for ComfyUI — MCP server + sidebar agent that generates images, video & audio, authors and runs workflows, and edits your live graph in natural language on ANY LLM (Claude, ChatGPT, Gemini, offline Ollama, or any hosted model). 178 tools, 36 AI skills, 55 installer packs. Local, LAN, VPS, or Comfy Cloud.
v0.1.0 · MIT
为 DeepSeek Harness 带来「跨会话长期记忆 + 后台自我进化」能力的纯插件实现:五轨记忆 · git 分支感知 · 回合内自我审查 · 技能自我进化与技能管理器 · 四轨待办 · COI 调度 · 会话广播 · 会话搜索 · 提示词管理器 · 临时信息便签——零核心修改、零运行时依赖,随装随用、卸载即净。
— · MIT
Reusable project context and specialist workflows for the AI tools you already use. AIWG places agents, skills, commands, and rules in provider-readable locations, with optional utilities for artifact memory, workflow orchestration, recovery, and discover
— · AGPL-3.0
The agentic workspace where people and agents work together in the loop.
v1.0.0-rc.2 · Apache-2.0
官方 DeepSeek Harness 的交互式终端 UI 插件:自研 ANSI 极简交互渲染、流式 Markdown/工具卡、16+ 主题、slash 命令与选择器、输入历史与本地偏好持久化、LSP 诊断、memory记忆,很丝滑的开发体验。
v3.0.0 · Apache-2.0
Content-aware output compression for AI coding assistants. 36 specialized processors cut CLI output tokens by 60-99% (git, pytest, npm, terraform, kubectl, docker, and more) without losing errors, diffs, or stack traces.
v1.0.11 · Apache-2.0
DSH Archive Manager — 在 DeepSeek Harness 中安全查看、恢复和管理已归档会话 · Safely view, restore, and manage archived sessions in DSH
v0.2.5 · MIT
Claude Code usage governor: compact professional output, context slimming, tool-output filtering, telemetry, and drift guardrails.
v0.12.10 · Apache-2.0
Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the session log (approval/asked -> autoReview/verdict -> approval/decided).
— · MIT
Personal Context Manager for Claude Code. Your life in walnuts.
v0.2.5 · MIT
A portable memory protocol for AI agents — load it as standing rules; a curation discipline + reference spec + optional cap hook.
v0.3.8 · Apache-2.0
Local-first, self-hosted AI agent runtime and MCP bridge with sandboxed sessions, memory, credentials, audit/replay, and a local Console.
v0.9.3 · MIT
A local Git-backed long-term memory bundle for DeepSeek Harness
v5.24.1 · Apache-2.0
Persistent memory for Claude Code, Cursor and Codex. Facts are typed, sourced, and retired when they change. Local SQLite, no API keys.
v0.20.0 · MIT
Local RAG MCP Server - Easy-to-setup document search with minimal configuration
— · Apache-2.0
Self improving agents through iterations
v0.6.0 · MIT
Domscribe is a pixel-to-code development tool that bridges the gap between running web applications and their source code.
v0.21.4 · MIT
The most accurate, cheapest and fastest memory for coding agents: searchable session history from Claude Code, Codex, Cursor and 32 more agents, already on your disk. No LLM, one Go binary.
v0.7.9 · Apache-2.0
Claude Code-style declarative permission rules for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), and workspace-path matching on the tools/pre-execute waterfall, session-log audit, and HMR reload.
v1.53.0 · MIT
Memory for AI agents that learns what is wrong and stops repeating it. Mark a memory wrong and it stops coming back; newer facts replace old ones. Local SQLite store and MCP server, persistent across sessions; hippo init wires it into Claude Code, Codex, Cursor, OpenClaw, OpenCode and Pi. Zero runtime deps, MIT, opt-in hosted TypeSafe Jev reranker.
v0.2.94 · MIT
Recent memories stay detailed. Older ones grow concise. Important ones live on.近期记忆保持详细,旧记忆逐渐精简,重要记忆长期存在。
v5.1.0 · MIT
You say it. AutoCode ships it. 48 skills. Code to deployment in one session. iLang v5.0 judgment + secret-safe deploys. Free forever.
v0.5.1 · MIT
A calibrated context sieve for Claude Code: every tool result is judged by a System One model before it enters context.
— · MIT
Bridge Deepseek-harness into Claude Code for review, critique, delegation, and session import.