v0.1.0-private.1 · no license
Support dsh runtime on Multica.
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.
v1.0.3 · MIT
OpenBitFun combines a high-performance agent runtime written in Rust with a polished desktop application. It pairs the depth of a Code Agent with open, general-purpose capabilities for work beyond software development.
v0.8.15 · MIT
A library for patching, replacing and decorating DeepSeek Harness plugins during runtime
— · Apache-2.0
Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.
— · Apache-2.0
ANOLISA (Agentic Nexus Operating Layer & Interface System Architecture) | Agentic OS with runtime, security, observability, and Tokenless response compression for lower token usage and cost.
— · MIT
Runtime evidence that helps agents trace, profile, and burn down hotspots in application and native code, GPU kernels, and inference stacks.
v0.5.21 · MIT
Composable, view-based memory for DeepSeek Harness. Pluggable sources and strategies, with three-tier memory out of the box.
v0.1.0 · Apache-2.0
A temporal context graph, a memory API, retrieval primitives, and a multiple-platform integration mesh — designed to be embedded into any host process.
— · MIT
Your pocket agent. Local-first AI agents on iOS and Android — real workspaces, tool execution with approvals, and your choice of model (DSH · Claude Code · Codex · GLM).
— · MIT
Community Docker and Kubernetes packaging for DeepSeek Harness (@deepseek-ai/dsh), with a hardened image, Compose stack, Helm chart, Web UI, and headless CLI.
v0.3.3 · MIT
dsh-routing-suite — injector + router-standard kit: install the runtime injector first, then the task-aware reasoning-mode router preset (measured P1-P23).
v0.3.6 · Apache-2.0
Give DeepSeek Harness a real office environment. Univer Office Plugin brings spreadsheets, docs, slides, canvases, relational tables, and more into one runtime — with connected data, validation, versioned changes, and isolated worktrees for multi-agent collaboration.
v0.1.0 · Apache-2.0
LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with DeepSeek Harness, Claude Code, OpenClaw, and any agent runtime.
v0.1.7 · Apache-2.0
Native local Taskboard plugin for DeepSeek Harness. SQLite-backed projects, Agent claim/review, and a native Web UI — no iframe, no second chat runtime.
v0.2.0 · MIT
一套 DSH runtime,Desktop、Web 与 TUI 三种开发体验。
v0.6.2 · MIT
deepseek-harness for vscode .A native VS Code coding-agent extension for DeepSeek Harness. Streamlined workbench with session management, streaming Markdown, slash commands, plugin center, and zero-deployment runtime — no WebUI served, no Harness setup
v0.5.1 · MIT
A DeepSeek Harness (dsh) plugin — turns dsh web into a SillyTavern-style roleplay frontend: character cards, prompt presets, lorebooks, personas, BM25 long-term memory, world-state deltas, and rollback-able floor operations, all on the dsh agent runtime.
v0.13.1 · MIT
DSH notification & remote-control plane: 28 outbound channels, 6 inbound controls, Native Notify & Control UI, live hot-apply, zero runtime deps.
v0.2.32 · MIT
Background automation runner for DSH: isolated agent runs, script/HTTP/SSH/Docker runtimes, cost guard, notifications, heartbeats.
v1.5.9 · MIT
DeepSeek Harness 原生桌面版,基于 Tauri 2,内置 Node.js 运行时,一键安装,极速启动,托盘常驻,自动更新。DeepSeek Harness native desktop version: built on Tauri 2 with a bundled Node.js runtime.
v4.0.0 · Apache-2.0
A 267-skill research graph in pure markdown — 51 research operations built from 216 single-purpose steps, composed in any order with explicit backtracking. One npx install, no runtime, no MCP bindings. The AI is the researcher; you set the direction.
v0.1.12 · MIT
Oh My Pi bash runtime ported as a deepseek-harness tool plugin: persistent shell session, output minimizer, managed background jobs, command interception
— · MIT
Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 14 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot, Kiro and more.