v0.1.0-private.1 · no license
Support dsh runtime on Multica.
v0.3.0 · MIT
Three-tier memory control plane for DeepSeek Harness: persistent runtime context, searchable project documents, pluggable long-term memory, smart routing, supervised agent workflows, WebUI, and headless tools.
v0.3.7 · Apache-2.0
Local-first AI agent runtime with sandboxed sessions, MCP tools, memory, credentials, audit/replay, and a built-in console. Run OpenAI, Anthropic, MiniMax, DeepSeek V4, and OpenAI-compatible models on your infrastructure.
v0.7.3 · MIT
A library for patching, replacing and decorating DeepSeek Harness plugins during runtime
v0.2.19 · MIT
BitFun 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.
v2.0.0 · Apache-2.0
Deterministic Runtime Execution Governance & Security Circuit-Breaker for DSH & Multi-Agent Workstations
v2.4.13 · SEE LICENSE IN LICENSE
AI Agent runtime authorization & evidence verification — tool-call GuardrailProvider, CCS 7-dimension verification standard, MCP/DSH security scanner, SSRF/command-injection/credential-exfil blocking with Ed25519 signed receipts.
— · 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.
— · 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.
— · MIT
Runtime evidence that helps agents trace, profile, and burn down hotspots in application and native code, GPU kernels, and inference stacks.
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
Community Docker and Kubernetes packaging for DeepSeek Harness (@deepseek-ai/dsh), with a hardened image, Compose stack, Helm chart, Web UI, and headless CLI.
v0.1.0 · 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.
v0.1.9 · MIT
一套 DSH runtime,Desktop、Web 与 TUI 三种开发体验。
v1.5.4 · 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.
v0.9.0 · MIT
管线管理内核(pipeline-kernel):单向任务链的任务板/台账/注册表/巡检/播种/打包/自愈。v0.9.0:rc.8 削薄工程(依赖对齐 rc.8、DshAgentRuntime 窄收口、webServer inject、domain/changed 统一失效、契约测试、CI 全量门禁;业务语义与入口冻结)。
v0.8.1 · MIT
Auditable vision and cross-platform Computer Use runtime for DeepSeek Harness with source-preserving evidence.
v0.1.0 · Apache-2.0
Open-source Claude Managed Agents API implementation and self-hosted Claude Tag-style agent runtime. Drop-in compatible; runs on Cloudflare Workers/Durable Objects or Node.js. Apache 2.0.
v0.2.9 · MIT
Desktop cockpit for DeepSeek Harness (dsh): token usage & cost tracking, budget alerts, runtime auto-update with rollback, Quick Ask hotkey, scheduled tasks, session search. Win+macOS. DeepSeek Harness 桌面驾驶舱:成本/用量监控 · 自动更新 · 定时任务
v0.5.5 · Apache-2.0
本地优先、零普通运行时依赖的 DSH 项目记忆:有界会话冻结 Hot Memory、倒排 BM25 召回、生命周期与缓存命中优化、中英双语 GUI。 / Local-first DSH project memory with zero regular runtime dependencies: bounded session-frozen Hot Memory, inverted-index BM25 recall, lifecycle, cache-aware design, and a bilingual GUI.
v0.3.74 · MIT
One macOS app for Claude Code, Codex, and every agent runtime you use — scheduled runs, global hotkey launcher, per-run git worktrees, one review board.
v0.5.0 · Apache-2.0
Claude Code outputStyles-equivalent runtime output-style switching for DeepSeek Harness
— · MIT
dsh-routing-suite — injector + router-standard kit: install the runtime injector first, then the task-aware reasoning-mode router preset (measured P1-P23).
— · MIT
Agent OS: the agent gets smarter on its own. We just hold the line: the grading command and expected result never make it into the success contract we hand it. Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 13 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot, Kiro and more.