Coding tools

Free / OSS · Apache-2.0 · 49.7k GitHub stars

VerdictThe open-source terminal coding assistant for API-key purists.

CatchYou are paying per-token at API rates—can exceed subscription costs on heavy use. No managed infrastructure; you are the ops team. Less polished than commercial alternatives.

Free / OSS · Apache-2.0 · 70.7k GitHub stars

VerdictMaximum control for developers who approve everything.

CatchHuman-in-the-loop means constant interruptions. Large tasks require many approvals. The pace is slower than autonomous alternatives.

Free / OSS · Freemium · 130k GitHub stars

VerdictOpenAI’s answer to terminal agents — open CLI, paid models; budget the plan or the API.

CatchThe CLI is open source, but the models are not free: you pay through ChatGPT plan quotas or API spend. Codex Web runs on OpenAI’s cloud, not on your machine. The install.sh, brew and npm routes are supply-chain choices, so pin a release binary when that matters. Vs Claude Code or OpenCode: this is OpenAI’s first-party agent, tied to ChatGPT plans or OpenAI API keys.

Free / OSS · OSS/MIT

VerdictSelf-hosted Devin alternative for teams who want control.

CatchHeavier than lighter agents like Goose. Self-hosting autonomous agents requires infrastructure and monitoring. The autonomy that makes it powerful also makes debugging failures harder.

Free / OSS · Apache-2.0 · 107k GitHub stars

VerdictGoogle terminal agent. OSS CLI remains, but consumer quota was cut 2026-06-18; Antigravity (agy) is the consumer path. Gemini-bound by design.

CatchGemini-bound lock-in—not model-agnostic like Goose or Crush. Consumer access (free/Pro/Ultra Google login) ended 2026-06-18; enterprise and API keys still work. Don't build on the old Google-login quota path. The OSS CLI remains. Antigravity CLI is the successor, not a 1:1 swap. Preview/nightly channels move fast; pin stable for production workflows. Enterprise path pushes you toward Vertex AI and Google Cloud project setup.

Free / OSS · Open-Core · 28.7k GitHub stars

VerdictThe beautiful, model-flexible TUI coding agent. Charm quality.

CatchLicensed FSL-1.1-MIT (competing-use restriction; source-available; MIT after two years—not OSI open-source). Pre-1.0 energy—config is migrating from JSON to crushrc Bash. Not a fully autonomous SWE agent like OpenHands; you stay in the loop. Hyper is Charm own model path if you want a subscription. Metrics on by default (DO_NOT_TRACK / CRUSH_DISABLE_METRICS to opt out).

Free / OSS · OSS/MIT · 219k GitHub stars

VerdictMIT BYOK agent across CLI/desktop/IDE. The real catches are on /log: date stamp and compaction.

CatchTwo catches worth reading on /log: “The date stamp is a trigger channel” (auto today’s-date × open-weight LoRA as a time-release fuse) and “Compaction ate the denial” (long sessions prune hard vetoes; compaction is untrusted rewrite). Re-read those two notes before you treat OpenCode as set-and-forget.

Free / OSS · OSS/MIT · 27.7k GitHub stars

VerdictMIT IDE+CLI agent with MCP marketplace. Roo’s active heir, not a second OpenCode.

CatchPitch IDE+platform, not “another OpenCode.” Gateway/account is convenience; BYOK stays. Marketplace and modes are the differentiator vs plain CLI harnesses. Enterprise governance rides Anaconda — evaluate if that middle layer matters for your org.

Free / OSS · OSS/MIT · 20.6k GitHub stars

VerdictMIT research SWE harness. Prefer mini-swe-agent going forward per maintainers.

CatchVs OpenHands (productized self-host SWE) and Devin (hosted autonomous): SWE-agent is research OSS, not a polished product seat. Maintainers recommend mini-swe-agent as the successor (simpler control flow; active development). For SWE-bench numbers, read upstream.

Free / OSS · AGPL-3.0 · 68.6k GitHub stars

VerdictApache-2.0 open-model terminal agent. Use the Rust line; classic Python is a fork.

CatchVs Claude Code / Cursor / OpenCode / Gemini CLI: this is open-model/BYOK terminal, not a hosted Max seat. 2026 rewrite — Rust Codex fork; classic Python AGPL lives at endolith/open-interpreter community fork. The old pip interpreter UX is no longer current upstream.

Free / OSS · OSS/MIT · 22.2k GitHub stars

VerdictMIT persistent REPL agent for RLM and continual self-refine loops. Interesting for research and harness work; never mistake the runtime for a sandbox.

CatchVs Pi, OpenCode, and OpenHands: this is the PrimeIntellect product, not the Pi coding agent, a general terminal wrapper, or a full autonomous developer platform. Prime Agent is not a security sandbox — its Python execution runs with the permissions you give it. Isolate it yourself before handing it credentials, production access, or untrusted tasks.

Free / OSS · OSS/MIT · 14.3k GitHub stars

VerdictMIT tiny agent seed with unusually broad control. Useful to study and adapt in a disposable box; too privileged to run casually on a personal host.

CatchVs Cua, OpenClaw, and Browser Use: GenericAgent is the tiny self-evolving seed with full system control, not a browser/computer-use protocol, messaging agent, or browser automation framework. Arbitrary OS and ADB control means a bad instruction can reach the host or a connected device. The Chinese README installer also uses plain HTTP — inspect and pin what you execute; do not grant it secrets by default.

Free / OSS · Apache-2.0 · 1.2k GitHub stars

VerdictApache-2.0 coding-runtime MCP when chat clients need workspace-jailed hands — not Desktop Commander host OS control; mid-★ Agents/MCP fill.

CatchVs Desktop Commander MCP: that is desktop-host terminal/files/processes; this is the chat-client→coding-agent hands layer (patches, interactive sessions, git) for any MCP client. Mid-★ (~1158) kept as Agents/MCP fill — Landlock is Linux-only; use Docker/VM for untrusted work.

Free / OSS · OSS/MIT · 24k GitHub stars

VerdictMIT in-process coding agent when you want the antirez shared-KV quants — not Ollama, not Magnitude, not llmfit.

CatchNot a generic GGUF runner. Project quants only: DeepSeek V4/V4.1, GLM 5.x, Qwen3.8. Vs Ollama / Magnitude / llmfit: Ollama is the general local model runner, Magnitude is the consumer profiler plus agent-harness wiring, llmfit only sizes models to hardware — DwarfStar 4 is the antirez in-process coding agent with a shared KV cache, not a general local runner. Still beta; pin a commit before a fleet bet.

Free tier · Freemium

VerdictAI assistant in your existing chat apps. Mind the security surface.

CatchHuge security surface. Every connected channel is a potential attack vector. You are trusting OpenClaw with access to your messaging platforms and the code it writes. Evaluate carefully for sensitive work.

Free tier · Freemium · 2.6k GitHub stars

VerdictGoogle freemium terminal agent. Consumer successor to Gemini CLI; still Gemini-bound.

CatchVs Gemini CLI (OSS @google/gemini-cli): Antigravity is the product successor for free/Pro/Ultra consumers — not a 1:1 flag clone (MCP config paths differ). Vs Claude Code / Cursor / OpenCode: Gemini-bound Google stack, not BYOK-agnostic. Enterprise Gemini CLI API/Vertex paths can remain; check which quota you are on.

Paid-led · Paid

VerdictThe best terminal agent for complex multi-file work. Budget for Max tier.

CatchThe $200/month Max plan is what serious users need—the cheaper tiers hit limits fast on large codebases. Token consumption on big repositories gets expensive. There is no autocomplete; this is for delegating tasks, not for inline suggestions while you type.

Paid-led · Freemium

VerdictThe best all-in-one AI coding experience. Worth the editor switch.

CatchYou are switching editors—VS Code extensions mostly work, but not all. Cursor closes, your background agents stop. The context can drift on very large refactors; you will need to guide it back.

Paid-led · Paid

VerdictBest for clean, well-defined tickets you want to hand off entirely.

CatchDevin is paid. The $500/month price prices out small teams. Success rates drop sharply on vague tickets; this is not a free coding agent.