Google's autonomous coding agent powered by Gemini 2.5 Pro. 2.28M beta visits, 140K+ code improvements shared. Unique proactive task scanning (finds TODOs and proposes work unprompted). Free tier: 15 tasks/day. No published SWE-bench scores.
Where it wins
Google backing ensures longevity and resources
Proactive task scanning — only tool that finds work to do unprompted
2.28M beta visits, 140K+ code improvements shared
Most generous free tier: 15 tasks/day
Jules Tools CLI + API enable integrations
534 + 339 HN pts — strong community engagement
Where to be skeptical
Every independent review: 'more of a demo than a daily driver', 'underwhelming performance'
No published SWE-bench scores — notable absence
MorphLLM: Tier 3 ('worth watching, not yet defaults')
Frustrating context window limits and inconsistent quality
Editorial verdict
Google-backed with a unique proactive scanning feature, but every independent review says 'not yet a daily driver.' Notable absence of SWE-bench scores. Best for free experimentation.
Videos
Reviews, tutorials, and comparisons from the community.
These secret Google AI’s will make you superhuman
Google Jules 3.0 UPDATE: FULLY FREE Async AI Coder IS INSANELY GOOD! (Jules API, Tools, CLI, & More)
Easily Automate Your Coding With Google Jules - Beginner Tutorial
Related
Claude Code
98Anthropic's official agentic coding CLI. v2.1.81 (Mar 20) shipped `--bare`, smarter worktree resume, and improved MCP OAuth while the repo crossed 82,204 stars and logged ~14 commits/week across 10+ maintainers. Terminal-native, tool-use-driven, with deep file system + shell access, #1 SWE-bench Pro standardized (45.89%), ~4% of GitHub public commits (SemiAnalysis), $2.5B annualized revenue. 8M+ npm weekly downloads. Opus 4.6 with 1M context.
OpenHands
88Category leader in multi-agent orchestration — 69,352 stars (verified), $18.8M Series A, AMD hardware partnership, 455 contributors, 1M downloads/month PyPI (3.4M all-time). SWE-Bench Verified 72% with Claude 4.5 Extended Thinking (updated 2026-03-19), Multi-SWE-Bench #1 across 8 languages. Gap to #2 is enormous on every axis.
Gemini CLI
88Google's open-source terminal agent with Gemini 3 models, 1M token context, built-in Google Search grounding, and the best free tier in the category (60 req/min, 1K req/day). v0.35.0 (Mar 24) shipped keybinding, policy, and telemetry fixes while the repo hit 98,957 stars and 12,593 forks. Terminal-Bench 2.0: 78.4% (#1). SWE-bench Pro standardized 43.30% (#3). Plan Mode added March 2026. First-pass correctness ~50-60% (Educative.io).
Codex CLI
87OpenAI's open-source coding agent built in Rust. Terminal-Bench 77.3% (#2), SWE-bench Pro standardized 41.04% (GPT-5.2-Codex). GPT-5.4 shipped March 5, 2026. Codex Security agent adds appsec capabilities. 3-4x more token-efficient than Claude Code, 240+ tokens/sec. Free with ChatGPT subscription, sandbox-first execution. 1M+ first-month users. Cleanest security record in Tier 1 — no documented incidents.
Public evidence
2.28M beta visits and 140K+ code improvements shared. Powered by Gemini 2.5 Pro. Proactive scanning for TODOs is unique in category.
Strong community engagement signal. But comments consistently note 'not yet a daily driver' and 'underwhelming performance.'
Jules placed in Tier 3 alongside other 'worth watching' tools. Not yet recommended as a default.
Raw GitHub source
GitHub README could not be fetched right now.