autopilot vs Pi vs uji Up to four tools, row by row. We do not guess: a cell we have not checked says so.
How they differ Model providersautopilot 27 · Pi 36 · uji 24 · 17 in all
autopilotAmazon Bedrock , MiniMax , vLLM , Vercel AI Gateway , Azure OpenAI , Cloudflare Workers AI , Cloudflare AI Gateway , LiteLLM Proxy , +2 more model providers DeepInfra , Requesty
+ providers you add PiAmazon Bedrock , MiniMax , OpenCode Go , vLLM , Hugging Face , Vercel AI Gateway , Azure OpenAI , OpenCode Console (OpenCode Zen) , +11 more model providers Alibaba (Qwen) , Xiaomi , NVIDIA , Baseten , Meta AI (Llama) , Cloudflare Workers AI , Cloudflare AI Gateway , Microsoft Foundry (Azure AI Foundry) , Ant Ling , Radius , SGLang
+ any OpenAI-compatible endpoint ujiOpenCode Go , Hugging Face , OpenCode Console (OpenCode Zen) , NVIDIA , Baseten , Perplexity , Cheaper Inference + providers you add Show 17 shared OpenAI , Anthropic , Google , OpenRouter , Ollama , SpaceXSI (Grok) , DeepSeek , LM Studio , +9 more model providers Moonshot AI , Z.ai , Groq , Fireworks , Mistral , GitHub Copilot , Together AI , Cerebras , llama.cpp
Pick this if…
PiPick this if you want a minimal agent harness you can customize.
Paraphrased from each maker’s own description. Select a line for the quote.
Checked for autopilot and Pi, not yet for uji: Price (autopilot: Free (open source) ; Pi: Free (open source) ), Bring your own key (autopilot: Yes ; Pi: Yes ), Editors and systems (autopilot: Terminal , macOS , Windows , Linux ; Pi: Terminal , macOS , Windows , Linux )
Not yet checked for any of these tools: agents it runs.
Provider names use the same listing as each tool page. Dotted values open their quote. A capability not shown is not yet checked; the tool may still have it.
Add a tool Claude Code CLI Codex CLI OpenCode oh-my-pi Hermes AgentAt a glance Mindshare HN mentions, 90 days Adoption GitHub stars, not scored autopilot
221 Pi
123k uji
Not yet checked Release days last 90 days autopilot
34 Pi
19 uji
Not yet checked Platforms listed surfaces autopilot
4 Pi
4 uji
Not yet checked Readers who say they use it I use autopilot I use Pi I use uji
Already use any of these? Tick it. Several is fine.
Votes can only raise a score: up to 20% of it reflects votes, graded on a curve against the most-voted tool. The square-root curve has a floor of 100 effective votes. Votes decay with a 90-day half-life. Maker self-votes do not count. Counts below 10 are hidden for display only. A vote is a signed-in reader ticking “I use this”. Since votes joined the score on 18 Nov 2026, the score is 80% mindshare plus 20% of the greater of mindshare and the vote score. GitHub stars do not affect the Index score. Mindshare uses a log scale; votes use the square-root curve and a 100-vote floor. Ranks use unrounded scores. Mindshare and adoption bars are log-scaled; the others are linear within this comparison. How the score is built
Open placement Comparison band: $149 a month per spot, 3 spots, no sponsor right now . Advertise here Differences only 3 of 4
Pi Earendil Works · CLI agent Interface
What it is
Open-source terminal coding agent and SDK.
Minimal, extensible agent harness that you can make your own
Modular coding agent whose components can be swapped at runtime
Pricing
Starts at (billing shown)
Not yet checked
Free tier
Not yet checked
Plans
Not yet checked
Bring your own key
Yes
Yes
Not yet checked
Runs on
Linux
Yes
Yes
Not yet checked
Terminal
Yes
Yes
Not yet checked
Windows
Yes
Yes
Not yet checked
macOS
Yes
Yes
Not yet checked
Models and agents
Model providers
OpenAI Anthropic Google OpenRouter Ollama SpaceXSI (Grok) DeepSeek Amazon Bedrock +19 more model providers LM Studio Moonshot AI Z.ai Groq Fireworks Mistral MiniMax GitHub Copilot Together AI vLLM Vercel AI Gateway Azure OpenAI Cerebras llama.cpp Cloudflare Workers AI Cloudflare AI Gateway LiteLLM Proxy DeepInfra Requesty
+ providers you add OpenAI Anthropic Google OpenRouter Ollama SpaceXSI (Grok) DeepSeek Amazon Bedrock +28 more model providers LM Studio Moonshot AI Z.ai Groq Fireworks Mistral MiniMax GitHub Copilot OpenCode Go Together AI vLLM Hugging Face Vercel AI Gateway Azure OpenAI Cerebras llama.cpp OpenCode Console (OpenCode Zen) Alibaba (Qwen) Xiaomi NVIDIA Baseten Meta AI (Llama) Cloudflare Workers AI Cloudflare AI Gateway Microsoft Foundry (Azure AI Foundry) Ant Ling Radius SGLang
+ any OpenAI-compatible endpoint OpenAI Anthropic Google OpenRouter Ollama SpaceXSI (Grok) DeepSeek LM Studio +16 more model providers Moonshot AI Z.ai Groq Fireworks Mistral GitHub Copilot OpenCode Go Together AI Hugging Face Cerebras llama.cpp OpenCode Console (OpenCode Zen) NVIDIA Baseten Perplexity Cheaper Inference
+ providers you add Models
Not yet checked
Anthropic OpenAI DeepSeek NVIDIA NIM Google Gemini Mistral Groq Cerebras xAI OpenRouter Vercel AI Gateway MiniMax Moonshot AI Qwen Meta Hugging Face Fireworks Together AI Baseten
Not yet checked
Source and activity
Source
Not yet checked
GitHub stars
Not yet checked
Release days, last 90 days
Not yet checked
Release days per week
Not yet checked
Latest release, any channel
Not yet checked
Index score
Score and rank
8 #153
Score 7.5; ranked on the unrounded score 78 #4
Score 77.9; ranked on the unrounded score 12 #107
Score 11.9; ranked on the unrounded score Mindshare
8
1 Hacker News mention in the last 90 days 78
1,310 Hacker News mentions in the last 90 days 12
2 Hacker News mentions in the last 90 days Adoption, not scored
44
221 stars, read 18 Nov 2026 96
122,575 stars, read 18 Nov 2026 Not yet checked
Rank history
First ranked 18 Nov 2026
First ranked 18 Nov 2026
First ranked 18 Nov 2026
Full page
Watch autopilot vs Pi vs uji on YouTube