Coding agent products (IDEs, CLIs, full suites)

Turnkey coding agents you install and run: IDE extensions, terminal CLIs, Dockerized workspaces. Each entry notes which part is the harness (the agent loop, tool wiring, approval model) versus the UI shell (VS Code extension, TUI, browser client).

#ProjectStarsTierOSSDescription
1opencode
mcpprovider-agnosticclituitypescript
192kslightly complexOpen-source terminal coding agent (formerly `sst/opencode`; transferred to anomalyco). The **harness** is a multi-provider tool-call loop (Claude, OpenAI, Gemini, local) with strong plugin and MCP support; the TUI is the shell. 100% OSS, very actively shipped.
2Gemini CLI
mcpclitypescript
106kslightly complexGoogle's first-party terminal agent for Gemini. The **harness** is the plugin/MCP tool-call loop; the terminal is the shell—Google's parallel to Claude Code / Codex, not just an API.
3Codex
sandboxprovider-agnosticcli
103kslightly complexOpenAI's terminal coding agent. The **harness** is the sandboxed tool-call loop with multi-provider support; the CLI is the shell. Reference implementation for "official CLI that ships code."
4OpenHands
memorybrowsersandboxpython
82.9kcomplex⚠️ (multi-license)Dockerized software-engineering agent. The **harness** is the bash/editor/browser toolset with micro-agents and event-stream session bridging; Docker is the sandbox. Main OSS choice for teams self-hosting autonomous repo work.
5pi
provider-agnostictuirust
82.2kslightly complexThe upstream AI agent toolkit behind this list's oh-my-pi fork: a unified multi-provider LLM API, agent loop, and TUI shell providing the **harness** that oh-my-pi's Rust rewrite builds on.
6Open Interpreter
clipython
67.5kmostly simpleLightweight terminal coding agent oriented to open models (DeepSeek, Kimi, Qwen). The **harness** is a code-execution loop — the model writes code, the harness executes it with confirmation gates; the CLI is the shell. The original "let the LLM run code on my machine" project, reborn for open weights.
7Cline
idetypescript
65.5kslightly complexVS Code extension whose **harness** is a plan-then-act loop with per-step human approval and cost transparency; the VS Code integration is the UI shell. Open-source counterweight to Cursor.
8goose
mcprust
52.1kslightly complexBlock-originated Rust agent, now stewarded by the Linux Foundation's Agentic AI Foundation (`aaif-goose/goose`). The **harness** is the MCP/ACP extension model with recipes and provider choice; there's no fixed UI slot—you bolt it into whatever shell you use.
9DeepSeek-Reasonix
memoryclituitypescript
28.8kslightly complexDeepSeek-native terminal coding agent. The **harness** is engineered around prefix-cache stability for long-running sessions; the TUI is the shell.
10vibe-kanban
27.6kslightly complexKanban-style fleet manager for running Claude Code, Codex, or any coding agent across many tasks at once. The **harness** contribution is the task-queue/review layer on top of whichever agent executes; not an agent loop itself.
11crush
memoryclitui
27kslightly complex⚠️ FSL-1.1-MITCharm's terminal coding agent (Charm's fork of the original OpenCode). The **harness** is the tool-calling loop with session persistence; the Bubble Tea TUI is the shell.
12Kilo Code
mcpcliidetypescript
26.7kslightly complexVS Code extension and CLI in the Cline/Roo-Code lineage — a natural pick now that Roo-Code is archived upstream. The **harness** is an approval-gated autonomous-mode loop with a provider/tool marketplace; the IDE is the shell.
13qwen-code
sandboxclitypescript
26.5kslightly complexAlibaba's official terminal coding agent, forked from Gemini CLI's agent loop and retuned for Qwen models. The **harness** is the same sandboxed tool-call loop as its upstream; the terminal is the shell.
14Symphony
sandbox
26.4kcomplexOpenAI's harness for fanning a task out into many isolated, autonomous coding-agent implementation runs and surfacing the ones that pass, so a team manages outcomes instead of supervising each session.
15Roo Code
mcpworkflowidetypescript
24.4kslightly complexVS Code/Cursor extension in the Cline lineage. The **harness** is the approval-gated agent with custom modes and a strong MCP story; the IDE is the UI. Popular community fork when you want that workflow without the upstream extension.
16oh-my-pi
browserprovider-agnosticcliiderust
21.2kslightly complexTerminal coding agent (fork of Pi) that wires the IDE into the **harness**: hash-anchored edits, a 32-tool loop tuned per-model, LSP rename/references/diagnostics on every write, a real DAP debugger (lldb/dlv/debugpy), long-lived Python + Bun execution kernels that call back into the agent's tools, browser control, and 40+ providers (Claude/OpenAI/Gemini/local). ~55k-line Rust core.
17jcode
mcpmemoryprovider-agnosticclirust
15.2kslightly complexRust terminal coding agent pitched as the most RAM-efficient **harness** in its class; MCP support, multi-provider (Claude/OpenAI).
18eigent
multi-agentlocal
14.7kcomplexOpen-source desktop **harness** positioned as a local, free alternative to Claude Cowork and Codex: multi-agent workspace orchestration in a self-hosted app rather than a hosted product.
19cc-haha
memorymulti-agenttypescript
13.9kcomplexLocal-first desktop workspace **harness** for Claude Code and other agents: multi-agent sessions, Git worktrees, code diffs, a skill marketplace, and chat-app access (WeChat, Telegram, WhatsApp).
20claw-code-agent
mcprustpythontypescript
537slightly complexPython reimplementation of the Claude Code agent architecture with zero external dependencies; interactive chat, streaming, plugin runtime, nested agent delegation, cost tracking, MCP transport—portable harness without the Rust/TS toolchain.
21AgentBox
sandboxtypescript
332slightly complexRuns multiple coding agents in parallel, each in its own sandboxed VM, locally or in the cloud, from one command. The **harness** contribution is the VM-per-agent isolation and fleet fan-out layer; whichever agent runs inside owns the loop.
22Proliferate
multi-agentsandboxidetypescript
156complexOpen-source AI IDE for Claude Code, Codex, OpenCode, and more. The **harness** contribution is the workspace/session orchestration layer: run multiple coding agents in parallel, locally or in the cloud, with isolated workspaces, reusable workflows, and shared team context.