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
Spielewoy/autoprompt-skill
Autoprompt is a skill distributed as an npm package that installs into an existing coding agent rather than replacing it. An interactive installer asks which agent is in use, confirms its configuration path and writes the adapter for that host; supported targets listed in the repository include Claude Code, Codex, OpenCode, Kilo Code, VS Code with Copilot, Prime Agent, Oh My Pi, DeepSeek Harness and Reasonix, each with an audited minimum version, plus a documented path for other command-line agents. The skill intercepts a coding request and expands it into a structured multi-agent run: the work is decomposed, delegated to subagents with defined roles, and passed through automated testing and code review before the result is returned, which is where the claimed reliability gain comes from. The command-line tool also provides a doctor command that checks each detected installation in strict mode, an update path that repairs an existing install, and interactive or per-provider uninstall. Requirements are Node.js 20 or newer, Python 3.11 with PyYAML exposed as python, Bash 4.3 on macOS or Linux, and git only when installing from a checkout. The project publishes its benchmark methodology rather than a bare claim: on Terminal-Bench 2.1 with OpenCode 1.18.7 the baseline solved 60 of 89 tasks and the same agent with Autoprompt solved 73, a gain of 14.61 points and 45 percent fewer failures, and the documentation separates that measured comparison from third-party leaderboard reference scores obtained under different setups. It also states the expected trade-off as roughly three times the wall-clock time and twice the token usage, marking those figures as planning estimates rather than measurements. Documentation covers run controls, the individual agents and worked examples.
https://github.com/Spielewoy/autoprompt-skill
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.