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
steipete/oracle
Oracle is a command line tool and MCP server that assembles a prompt together with a selected set of project files, sends that bundle to an AI model, and stores the result as a session. It targets developers and coding agents that want a second-model review grounded in the actual project rather than a summary of it. Context is controlled with repeatable --file arguments accepting individual files, directories, glob patterns and exclusions prefixed with an exclamation mark. Generated text bundles carry stable line numbers so answers can cite a path and line, and binary or large browser inputs can be uploaded or bundled without converting their contents. A --render mode prints the exact prompt and numbered file contents without credentials and without contacting a model, and --dry-run summary combined with --files-report previews the resolved file list and a token estimate before sending. Three execution paths exist: API mode for provider APIs and reliable automation, covering OpenAI, Azure OpenAI, Anthropic, Gemini, xAI, OpenRouter and compatible endpoints; browser mode which drives a signed-in ChatGPT session through Chrome automation or a cookie-based Gemini client; and render mode for inspecting and pasting the bundle by hand. Oracle chooses API mode when an OpenAI key is available and browser mode otherwise, and --engine makes the choice explicit. Runs are stored under ~/.oracle/sessions so long responses can finish in the background and completed answers can be replayed, with oracle status listing recent work, oracle session reattaching to a run, oracle restart repeating one, and --followup continuing a supported API or ChatGPT conversation with more context. The --models flag runs a panel of several models in one session and records per-model usage, cost, output and partial failures, while oracle doctor --providers checks readiness without exposing credentials. It installs through Homebrew or npm, requires Node.js 24 or newer, and integrates with Claude Code, Codex, Cursor and other MCP clients through an oracle-mcp stdio server or an installable skill.
https://github.com/steipete/oracle
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.