deepseek-ai/deepseek-harness
DeepSeek Harness (dsh) is an open-source agent harness from DeepSeek AI built on an everything-is-a-plugin architecture over the Cordis framework, started from npm with a local web UI.
Awesome AI Agents › AI Developer Tools
zhsama/claude-sub-agent
This repository packages a specification-driven development workflow as a collection of Claude Code subagents plus a slash command that orchestrates them. The pipeline starts from a project description and passes it through three phases. Planning uses a requirements analyst, a system architect and a task planner. Development uses an implementation agent and a testing agent. Validation uses a code reviewer and a final validator. An orchestrator agent drives the sequence, and a quality gate sits after each phase: when the gate fails, control loops back to the earlier agent instead of proceeding, so requirements failures return to analysis and implementation failures return to the developer agent. Each phase produces written artifacts, which the project treats as documentation generated as a side effect of the process rather than as a separate task. Beyond the core specification agents, the repository includes domain specialists organised into directories such as backend and frontend, and the workflow is designed to call existing specialised agents a team already maintains. Installation is a file copy: clone the repository or download individual agent files, create the .claude/agents and .claude/commands directories in the target project, copy the markdown definitions in, and add a documentation convention block to the project CLAUDE.md so generated tasks, specifications and design documents land in dated folders under docs rather than at the repository root. There is no runtime, package or dependency to install; the agents are markdown prompt files interpreted by Claude Code, so the project is best understood as a reusable prompt architecture for AI-assisted software delivery. It targets developers who already use Claude Code and want a repeatable structure with explicit checkpoints instead of ad hoc single-prompt coding sessions.
https://github.com/zhsama/claude-sub-agent
Also in AI Developer Tools
Hmbown/Codewhale
Open-source terminal coding agent written in Rust that edits files, runs commands and works toward a goal across many model providers.
TabbyML/tabby
Tabby is a self-hosted, open-source AI coding assistant providing a private and customizable alternative to GitHub Copilot with rich integration and deployment options.
cursor/cursor
Cursor is an AI-powered code editor designed to enhance programming productivity by integrating intelligent code suggestions and AI-driven features directly into the coding workflow.
oraios/serena
Serena is a free and open-source coding agent toolkit that enhances large language models with semantic code retrieval and editing capabilities, enabling autonomous coding workflows directly on your codebase.
QwenLM/qwen-code
Open-source terminal coding agent from the Qwen team with subagents, skills, hooks and MCP support, speaking the OpenAI, Anthropic, Gemini and Qwen API formats plus local model runtimes.
plandex-ai/plandex
Plandex is an open-source AI coding agent designed to plan, execute, and manage large-scale coding tasks and real-world projects with high efficiency and flexibility.
smol-ai/developer
Smol Developer is a library and toolset that embeds a junior developer AI agent into applications to scaffold and generate codebases interactively through human-in-the-loop prompt engineering.