AI Coding

DeepSeek Harness279.4k★

DeepSeek Harness (dsh) is DeepSeek's own agent app: the layer that gives a model a shell, files, tools, skills and a UI, for coding and everyday work like spreadsheets and slides. Every piece is a Cordis plugin, so you swap parts instead of forking. MIT licensed and free. npx @deepseek-ai/dsh web starts a local web UI on 127.0.0.1:3080, and DeepSeek now ships an official desktop app with a macOS download on its site. Add a DeepSeek API key, or point it at another provider or any OpenAI-compatible endpoint. Nothing to host. The harness costs nothing; tokens do. DeepSeek V4-Pro runs $1.32 per million input tokens and $3.96 per million output at weekday peak, half off-peak, and Flash is far cheaper. Built-in web search starts billing November 1. Solo and small teams: free, pin a version. Larger teams: wait. The catch: it's a developer preview, every release is still tagged pre-release, and DeepSeek's own safety notice says it hasn't had a security audit. August proved it: CVE-2026-82533 (CVSS 9.4) let a sandboxed agent switch off its own sandbox, fixed in 0.1.2-alpha.1. Run it in a VM. The desktop app also sends usage analytics by default, with no switch in the UI.

opencode226.3k★

opencode is an open-source AI coding agent that lives in your terminal. It is built by Anomaly, the team behind SST, and it is the project now hosted at opencode.ai (the old sst/opencode repo redirects here). Bring any model provider, Anthropic, OpenAI, Google, GitHub Copilot, or a local model, and it reads, writes, and edits files and runs shell commands from a clean TUI. MIT licensed. The design choice that sets it apart is a two-agent flow: a plan agent that only reads and analyzes, and a build agent that actually makes changes, so you review the plan before anything touches your code. It pulls in LSP diagnostics as it works. Install is trivial through npm, Homebrew, or a one-line script, with no Docker and no GPU. Supply an API key for a hosted model, or point it at a local one and run for nothing. The agent is still free and there are still no feature gates, but Anomaly now sells model access too. Zen is their gateway of models they have benchmarked for coding agents: pay per token with no subscription, several models free for now, GPT 5.6 Luna at $0.20 in and $1.20 out per million tokens under 272K of context, Claude Opus 5 at $5.00 and $25.00, GPT 5.5 Pro at $30.00 and $180.00. Balances auto-reload $20 when they drop below $5, and card processing of 4.4% plus $0.30 is passed through at cost. There is an enterprise track as well. Solo developers with existing API access should keep using it exactly as before. The catch is the model bill and the terminal-first workflow. opencode is free, but the models it drives are not, and heavy use adds up the same way a subscription would. For a graphical editor experience this is not it. It is a TUI first, with a desktop app still in beta.

codex135.0k★

Codex CLI is OpenAI's coding agent for the terminal. Point it at a repo and it reads files, writes code, and runs commands while you approve each step or let it run. The client is Rust, Apache 2.0, and free to install with a single command. There is nothing to host. The sandboxing is real rather than decorative: Seatbelt on macOS, bubblewrap on Linux and WSL2, with an approval mode that asks before the agent reaches the internet. The escape hatch is the part worth knowing about. Run codex with the --oss flag and it drives Ollama or LM Studio on your own machine, and the provider config accepts any OpenAI-compatible base URL. Anyone already paying for ChatGPT gets this at no extra cost. Teams weighing it against Copilot or Cursor should know it does no inline completion. It is a terminal agent plus an IDE extension, not an autocomplete engine. The catch is what Apache 2.0 actually covers. The license is on the wrapper, not the model. Codex runs on every ChatGPT tier including Free, but free buys you quick tasks and little else, and real work pushes you up through Go at $8 a month, Plus at $20, and Pro from $100. What the tiers sell is volume, not access. You can read and fork the client all you like; the intelligence behind it stays metered.

cline71.5k★

Cline is an open source coding agent: it reads your project, edits files, runs terminal commands and drives a browser, asking approval for each step unless you switch on auto-approve. It ships as a VS Code extension, CLI, desktop app and SDK, all Apache 2.0, plus a JetBrains plugin. Bring your own key from Anthropic, OpenAI, Google or OpenRouter, or run a local model through Ollama, and the agent costs nothing. Install from the VS Code Marketplace or npm i -g cline. Version 4 added a marketplace for skills, MCP servers and plugins, and Cline Cloud runs up to 10 tasks at once in remote sandboxes that push to a branch. Unlike GitHub Copilot or Cursor, it doesn't tie you to one editor or model vendor. Two ways to pay. ClinePass is $9.99/month for bundled open-weight models (GLM, Kimi, DeepSeek, Qwen and others) with no keys to manage. Enterprise is custom-priced: SSO, role-based access, central billing and VPC or on-prem deployment. Solo and small teams: free plus your own key. Organizations needing SSO: Enterprise. The catch: tokens are the real bill, and an agent that reads whole codebases burns them fast. The JetBrains plugin is also closed source.

oh-my-openagent70.9k★

OmO (Oh My OpenAgent) started as a plugin that supercharged OpenCode and Codex CLI and is now its own coding agent: one omo binary built on senpi, the team's fork of the pi agent. Add ultrawork to a prompt and it plans, routes subtasks to different models and keeps going until the job is done; mass ulw turns a job into a graph of agents. Install with a curl script or bun add -g omo-ai (the unrelated omo package on npm belongs to someone else). It runs a shared background daemon and keeps config in ~/.omo. It can sign in with Claude, ChatGPT, Kimi or GLM subscriptions and ships built-in web search, docs lookup and a browser. The old OpenCode and Codex plugins still work but get degraded support from here on. There's no paid tier; you pay for the models. But it isn't open source. The Sustainable Use License allows only internal business, non-commercial or personal use and bars commercial distribution or hosting. Solo devs experimenting with multi-model agents: fine. Companies building a product on it: no. The catch: telemetry is on by default and reports token counts, cost and which models ran. Releases ship several times a day, and the marketing leans hard on grand claims. Anthropic's terms also bar third-party apps from offering Claude.ai login, which is what OmO's subscription sign-in does, so check before you rely on it.

goose56.5k★

goose is an AI agent that runs on your machine and does the work instead of suggesting it: it edits files, runs commands and calls tools, for code or for research and data jobs. Block built it, then in April 2026 donated it to the Linux Foundation's Agentic AI Foundation. Apache 2.0, free, as a desktop app, CLI or API. Nothing to host. It plugs into 70+ MCP extensions and 15+ model providers. Two cheap paths are new: built-in local models with no Ollama and no API key, or your existing Claude Code or ChatGPT Plus/Pro subscription over ACP instead of per-token billing. Local models are slower and weaker at tool calling. There's no paid tier; the model is your only bill. Solo: free. Small teams: free, share recipes (reusable YAML workflows). Larger teams: free, and custom distributions let you ship a preconfigured internal build. The catch: autonomous mode is the default, so out of the box goose can modify and delete files without asking. Switch to Smart Approval first. In July, a high-severity advisory showed goose review in a malicious repo could run an attacker's command before any prompt (fixed in 1.44.0).

aider50.1k★

Aider is an AI pair programmer that lives in your terminal. Run it inside a git repo, say what to change, and it edits your files and commits each change with a sensible message, so every AI edit is one /undo away. It maps your whole codebase, works with almost any model including local ones, and it's free under Apache 2.0. Install with python -m pip install aider-install then aider-install; it pulls in its own Python 3.12 if needed. Bring your own API key and pay the provider. No account, no server, no paid tier, and analytics are opt-in. Solo devs and small teams: free, and a great fit if you already live in the terminal. Larger teams: fine per developer, but there's no admin console, so you govern keys and spend at the provider. The catch is maintenance. The last release shipped in February 2026 and the last commit in May, with a big open backlog. Newer Claude and GPT support sits on main, unreleased. It's also a pair programmer, not a hands-off agent: you pick the files. For that, look at Claude Code, Codex CLI or OpenCode. The community fork cecli is still shipping.

Codewhale41.2k★

Codewhale is a coding agent that runs in your terminal. Describe a task and it reads your project, edits files, runs commands, and checks the result, using whatever model you connect. It started life as deepseek-tui and is now provider-neutral: 44 provider IDs, from DeepSeek (still the default), OpenAI, Anthropic, and Google to local models through Ollama, vLLM, or SGLang. MIT licensed, written in Rust. Install is one curl command, or npm, Cargo, Docker, Nix, or Scoop, with builds for Linux, macOS, Windows, and Android under Termux. Then you add your own API key or point it at a local model server. Plan mode explores without touching files, work mode makes changes, and Shift+Tab switches between Ask, Auto-Review, and Full Access. A ChatGPT sign-in route bills against your subscription instead of an API key. Free at every team size today. You pay your model provider and nothing to Codewhale. anomalyco/opencode, openai/codex, and Aider-AI/aider are the closest alternatives. Pick Codewhale for DeepSeek-first defaults and a wide provider list in a single Rust binary. The catch: usage analytics are on by default until you run codewhale config set telemetry false. It is pre-1.0. And the company behind it, Shannon Labs, is building accounts, a hosted API route, and a closed-source desktop app. The terms promise to show a price before charging, which tells you prices are coming.

oh-my-pi38.8k★

Oh My Pi is an AI coding agent that lives in your terminal. It reads your code, makes edits, runs commands, and drives whole workflows. What sets it apart is that it wires in the machinery a real IDE uses: language servers for accurate renames and refactors, and actual debuggers (lldb, Delve, debugpy) so the model can step through running code instead of guessing. MIT licensed and completely free. Setup is a one-line install through curl, Homebrew, or Bun, and the same binary runs on macOS, Linux, and Windows with no WSL. It picks up rules, skills, and MCP servers from the config folders of Claude, Cursor, Windsurf, Codex, Cline, and Copilot. It works with more than 60 model providers, local runners like Ollama and llama.cpp included, and signs in with existing subscriptions like GitHub Copilot as well as API keys. The tool costs nothing. What you pay is the model bill, and a swarm of subagents plus browser automation runs that up faster than a single-threaded assistant. Solo devs and small teams comfortable in a terminal: this is a legitimate free alternative to a Cursor subscription. The catch is maturity. It is a hard fork of another young project, shipping several releases a week. A company, Stencil Labs, now stands behind it, but there is no support offering. Treat it as a powerful tool you are willing to debug.

DeepSeek-Reasonix36.2k★

DeepSeek-Reasonix is a coding agent that lives in your terminal and runs on DeepSeek's models. It edits files, runs shell commands, plans multi-step changes, and plugs into MCP servers and custom skills, the same shape as Aider or Claude Code but built specifically around DeepSeek. The agent itself is free and MIT licensed; you bring your own DeepSeek API key. The whole point is cost control through prefix caching. The project is engineered to keep your conversation prefix stable so DeepSeek's cache keeps hitting, and the numbers are real: one documented session ran about twelve dollars instead of sixty-one without caching. Install is a single npm install with Node 22 or newer. A Tauri desktop client exists but it is still a prerelease, so the command line is where the stable experience lives. Solo developers already paying for DeepSeek API access get a capable agent for nothing extra. Small teams that want AI coding without per-seat Copilot or Cursor bills can run this and pay only for tokens. Larger teams will weigh the lack of polish and support against the savings, and many will still want an IDE-integrated tool instead. The catch is that you are tied to one model family. DeepSeek is cheap and capable, but it is not the strongest coding model out there, and the project says so itself. If you need the best results regardless of cost, this is not it.

qwen-code29.5k★

Qwen Code is Alibaba's open-source answer to Claude Code: an AI coding agent that lives in your terminal, reads your repo, writes code, runs commands, and fixes its own mistakes. Apache 2.0 licensed, and unlike the proprietary agents it takes after, it is not locked to one model. Point it at Qwen's own API, OpenAI, Anthropic, Gemini, or a local model through Ollama or vLLM. The framework is free. What you pay is whatever the model behind it costs. Install is a one-liner through npm, Homebrew, or a curl script, then you configure an API key or a local endpoint. It ships more than a terminal: there are VS Code, Zed, and JetBrains plugins, a headless mode for scripting, and a daemon. Built-in skills like /review, /bugfix, and /loop cover the common agent workflows out of the box, and it speaks MCP for extending into your own tools. The real question is the model, not the tool. Run it against a strong hosted model and it competes with Claude Code and Cursor on capability while costing you only tokens. Run it against a local Qwen model and you get a fully offline coding agent for free, at the cost of some quality. Solo devs and cost-conscious teams get the flexible, no-lock-in option here. Teams already deep in Cursor's IDE experience may not switch. The catch: an agent is only as good as the model driving it. Free and local sounds great until a weaker model burns your afternoon on a task Claude would have nailed in one pass. The freedom to choose your model is also the freedom to choose a bad one.

grok-build27.7k★

Grok Build is SpaceXAI's terminal coding agent, the Grok answer to Claude Code. It reads your codebase, edits files, runs commands, and works through multi-step tasks in a full-screen TUI. It also runs headless for CI and plugs into editors through the Agent Client Protocol. The client is Apache 2.0. Install is one curl command, with prebuilt binaries for macOS, Linux, and Windows. First launch signs you into an x.ai account, and the product page says it is free to try, though the free tier's limits are not published. It is not locked to Grok either: the docs cover custom model endpoints, including OpenAI-style and Anthropic-style APIs and self-hosted models. Your MCP servers and skills carry over, because it reads the config files Claude Code and Cursor already use. Solo: free to try, then SuperGrok at $30/mo or SuperGrok Plus at $100/mo for more usage, or pay per token through the API. Team accounts get OIDC single sign-on and zero data retention. anomalyco/opencode and Aider-AI/aider are the community-run alternatives, and openai/codex is the same open-client, vendor-model play. The catch: open source here means you can read and build it, not shape it. The public repo is a periodic sync from a private monorepo, and outside contributions are not accepted. There are still no tagged GitHub releases, even though versioned binaries ship several times a month.

freebuff14.1k★

Freebuff is a coding agent you can use without paying: text ads cover the model bill. One account gets a CLI (npm install -g freebuff), a desktop app that runs parallel agents, a web app builder, a cloud runner for GitHub repos and a chat. Apache 2.0 code, no card, no API key. Self-hosting isn't the point: the public repo is a snapshot of a private one, and running it yourself means your own provider keys. Free usage is metered in hours, refilled daily: 30 hours on the cheapest MiMo model or 5 on Claude Haiku 5.5. Outside supported regions it drops to 5 hours a day (4 on a VPN). Paid plans now exist: Starter $8/month, Plus $25 and Pro $60, about 22% less billed yearly, for more hours and every model. Solo devs: free is real. Small teams: Starter for side projects. Larger teams: skip it for company code. The catch is the data deal. Freebuff analyzes your prompts, pasted code included, to target ads, and its apps can log text you type before you send it. Submissions to models labeled for AI training can be sold to third parties. Keep NDA work out of it.

claurst10.3k★

claurst is an open source terminal coding agent written in Rust, built to replicate the behavior of Claude Code. It reads files, runs commands, searches codebases, and handles git operations from your terminal. The project was built from behavioral specs, not copied source code. The appeal is obvious: Claude Code is a proprietary tool that costs money. claurst gives you a similar workflow for free (assuming you bring your own API key for whatever model you point it at). Being written in Rust means it starts fast and uses less memory than Node.js-based alternatives. The project grew quickly after the Claude Code source leak sparked interest in how these agents work under the hood. For developers who want a terminal coding agent but do not want to pay for Claude Code, this is the most direct alternative. Aider and Continue are more established options with broader model support and larger communities. claurst is newer and less battle-tested, but the Rust foundation and active development are promising. The catch: this is early-stage software riding a wave of hype. The feature set is thinner than Claude Code, the plugin ecosystem does not exist yet, and you are depending on a solo maintainer. If you need reliability today, the established tools are safer bets.

ZCode8.6k★

ZCode is Z.ai's own AI coding workspace, open sourced on September 20, 2026. Describe a task and an agent plans, writes, runs, and reviews the code, from a desktop app, a browser tab, or the terminal. It is built around Z.ai's GLM models but takes OpenAI, Anthropic, DeepSeek, Kimi, MiniMax, Qwen, xAI, and OpenRouter keys too. Apache 2.0, and Z.ai says the app itself is completely free. Official installers cover macOS, Windows, and Linux. Building from source needs pinned versions of Node and pnpm. You sign in with Z.ai or paste an API key, so there is nothing to host. This is a vendor source drop, not a community project yet: two commits, no tagged releases, and a Chinese-first README. Solo and small teams: free, and the cheap way in is the GLM Coding Plan, which starts at $18/mo. Medium and large teams: read the NOTICE file before rolling it out. For a more mature open agent, anomalyco/opencode is further along, and codewhale-hq/Codewhale is the terminal-only option. The catch is in that NOTICE file. There is no operating system sandbox. Headless runs with --prompt default to yolo mode, which waves ordinary tool calls through without asking. The Computer Use package is a placeholder that returns an error. And Z.ai does not promise the source matches the product it ships.

kimi-code8.2k★

kimi-code is a coding agent that runs in your terminal, built by Moonshot AI around their Kimi models. It reads and edits code, runs shell commands, searches files, fetches web pages, and decides its next move from the results, the same agent loop as Claude Code or Aider. It ships as a single binary with no Node install required, and supports subagents for parallel work, MCP servers, and lifecycle hooks. MIT licensed and free; you authenticate with a Moonshot API key or OAuth. Install is a one-line script on macOS, Linux, or Windows, and the single-binary design means there is nothing else to set up. This is early software, though, sitting at version 0.2.0. The agent works and the feature list is ambitious, with video input, subagents, and hooks, but expect the rough edges of a tool that shipped weeks ago, not one hardened over years. Solo developers already in the Kimi ecosystem get a capable terminal agent for the price of API tokens. Small teams curious about Moonshot's models can try it without committing to a subscription tool. Larger teams should wait for it to mature, or stick with a more established agent. The tool is free; your cost is Moonshot API usage. The catch is that you are betting on one vendor's models and a very young project. Kimi is capable, but if Moonshot changes pricing or the project stalls, you are stuck. Treat it as worth watching, not yet worth standardizing on.

gsd-27.7k★

GSD 2 has moved. It was a terminal coding agent that plans a project into milestones, runs each task in a fresh context window, commits to git and keeps going without you. On May 22, 2026 its maintainers moved development to the Open GSD organization, where it continues as GSD Pi, and this repo was archived on October 4, 2026. Free under MIT, then and now. The old gsd-pi npm package is deprecated and frozen at 3.0.0. GSD Pi installs from @opengsd/gsd-pi, restarted its version numbers at 1.0.0, and tells you to uninstall the old global package first so its binary doesn't shadow the new one. Bring your own model: API keys, OAuth, or Claude Code and Cursor Agent as backends. Solo and small teams: free; switch to GSD Pi and expect your model bill to be the real cost. Larger teams: wait. A hosted GSD Cloud is listed as coming soon, unpriced. The catch: the move landed the same day reports said the original creator deleted his accounts and sold off a crypto token that GSD 2's own README advertised. The old npm package still sits under his account. Check who publishes what you install.

gptme4.5k★

gptme is a coding agent that runs in your terminal and works with whatever model you point it at. It executes shell commands, writes and patches files, runs Python, browses the web through Playwright, and reads images, all from a single CLI. The model is your choice: Anthropic, OpenAI, Google, DeepSeek, or a local llama.cpp model when you want zero API cost. There's nothing to host. You pip install it, drop in an API key, and you're working. It also exposes a web UI and a REST API if you want to drive it from somewhere other than the terminal, and it speaks MCP, so you can plug in external tool servers. For something this capable, the setup is refreshingly light. Solo developers and tinkerers who live in the terminal and want a model-agnostic agent get the most here. It's a direct open-source answer to Claude Code, Copilot CLI, and Cursor, with the advantage that you're not locked to one vendor's model. Teams standardizing on a single coding agent may prefer something with more polish and support. The catch: the software is free, but the models aren't. Point it at a frontier API and you'll pay per token like any agent, run it on a local model and you trade that bill for slower, weaker output. And model-agnostic means you're the one tuning which model handles which job, that flexibility is also homework.

background-agents3.5k★

Background-agents lets you fire off AI coding agents that work on their own. You hand one a task, it spins up a sandboxed dev environment, clones your repo, does the work, and opens a pull request while you do something else. It is the self-hosted, open source take on what Cursor's cloud agents and Devin sell as a subscription. MIT licensed. Free to use is not free to run. This is a multi-service system: a Next.js web app, Cloudflare Workers, Python pieces, a GitHub App, and an account with a sandbox provider such as Modal, Daytona, Vercel Sandbox, OpenComputer or E2B. Models come through an Anthropic key or Claude subscription, a ChatGPT subscription for Codex, SuperGrok, or OpenCode Zen. The software is free; the sandbox and model bills are not. Sessions start from the web UI, Slack, GitHub pull requests, Linear issues or webhooks, and it runs scheduled and event-driven automations. One person does most of the maintenance, so treat it as capable but young. Solo devs and small teams who want autonomous coding without a per-seat bill get the most from it. Teams that need reliability and support today should pay for a hosted product. The catch is trust and ops. It is single-tenant by design: anyone whose role allows repository use can reach every repo the GitHub App is installed on, with no per-user access check. Add infrastructure you maintain and API bills you watch, and it only pays off if you value control over convenience.

kimchi2.3k★

Kimchi is a terminal coding agent from the team behind Cast AI, built on the pi agent SDK. Its twist is multi-model routing: an orchestrator splits a job into explore, plan, build and review steps and hands each to a different model, light ones for reading code, heavier ones for hard builds. The CLI is free and Apache-2.0. Install is one Homebrew or curl line, then kimchi setup. Every default points at Kimchi's hosted models (Kimi, MiniMax, Nemotron), and the docs assume an account. You don't strictly need one: it auto-detects local Ollama models and takes other providers' keys, but then you configure the role pools yourself. The paid side is hosted inference. Coder is $20/month with $25 of credits, max 3 seats. Teams is $35/seat/month with budgets and RBAC. Claude or GPT routed through Kimchi adds $0.20/$0.30 per million tokens on top of provider pricing. Solo: free with your own keys, or Coder. Small teams: Coder, then Teams past 3 seats. Larger orgs: Enterprise for VPC deploys. The catch: the CLI is a funnel for that inference business, and telemetry is on by default (usage metadata, not prompts) until you set KIMCHI_TELEMETRY_ENABLED=0.

smallcode2.0k★

smallcode is a terminal coding agent built for small, local language models, the 8B to 35B range you can run on your own hardware, not frontier models like Claude or GPT. Most agents assume a huge, reliable model behind them. smallcode assumes the opposite and engineers around it. MIT-licensed and free. The adaptations are practical: a managed context budget instead of dumping everything at the model, forgiving parsing for messy tool calls, TODO-file planning, and search-and-replace patches instead of full-file rewrites. It's actively maintained, with real releases and a benchmark harness. The project claims 87% on a benchmark with a 4B-active model, though it doesn't spell out the suite or baseline, so take the number as a signal, not proof. The catch: a coding agent is only as good as the model driving it, and small local models still make mistakes a frontier model wouldn't. If you want to keep code on your own machine or avoid API bills, this is a serious attempt at making that work. If you just want the best results, a frontier model with a mature agent like aider will still beat it.

pi_agent_rust2.0k★

A from-scratch Rust port of Mario Zechner's Pi Agent, done with his blessing. Single binary called pi, no Node runtime and no Electron shell, 28 built-in tools with 18 live in a default session, and streaming that holds up over a long conversation. The complaint it answers is startup time and memory, and it answers it by rewriting the engine rather than trimming the old one. Security is designed in rather than bolted on. Extension execution is capability gated across tool, exec, http, session, ui, and events, then a second stage mediates the command itself and blocks recursive delete, raw disk writes, and reverse shells by default. Extensions move through a trust lifecycle from pending to trusted to killed, with audit logs on the kill switch. More thought than most agent CLIs have given the problem. Install is a curl script, and the only recurring cost is the model API key you already have. The catch is the license, and it is a real one. GitHub's badge says MIT. The LICENSE file is MIT plus a rider that grants no rights whatsoever to OpenAI, Anthropic, or their affiliates, and forbids use in any training corpus, evaluation harness, or ML pipeline. Breach terminates the license automatically. That is not open source under the OSI definition.