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
darrenhinde/OpenAgents
OpenAgents Control, abbreviated OAC, extends the open-source OpenCode CLI with specialized coding agents, a context system and team workflows. Its premise is that generic AI agents produce code that does not match an existing codebase, forcing rewrites; OAC instead loads project patterns before generation so the produced code follows the same validation library, ORM and response conventions the team already uses. Agents are defined as plain markdown files that users edit directly, with no compilation and no proprietary format, so workflows, constraints and behavior can be customized and committed to the repository for the whole team to inherit. Execution follows a propose, approve, execute cycle: agents always request approval before acting, then work incrementally with validation between steps and delegate to specialist agents when needed. Context files are deliberately kept under two hundred lines and loaded lazily under what the README calls the minimal viable information principle, which the authors credit with a large reduction in token use. The system is model agnostic and works with Claude, GPT, Gemini, MiniMax or local models, and covers TypeScript, Python, Go, Rust, C# and other languages across both frontend and backend work. Installation is a single curl script that also sets up the OpenCode CLI when missing, with a separate update script and support for custom install directories; usage starts by invoking the OpenAgent agent from the OpenCode command line. A beta Claude Code plugin is offered as an alternative entry point. The README includes a comparison table positioning OAC against Cursor, Copilot, Aider and Oh My OpenCode along axes such as pattern learning, approval gates, token efficiency, team standards and execution speed, and recommends OAC for production code and teams with established conventions rather than for quick prototypes.
https://github.com/darrenhinde/OpenAgents
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.