Skip to content
ADE Index

CodeAF vs Hermes Agent vs oh-my-pi

Up to four tools, row by row. We do not guess: a cell we have not checked says so.

How they differ

oh-my-pi is a fork of Pi: omp is a fork of Pi by Mario Zechner, rewritten as a coding-first surface: sessions, subagents, slash commands, extensions — all TypeScript, all MIT, all on GitHub. github.com

Pick this if…

Paraphrased from each maker’s own description. Select a line for the quote.

Checked for Hermes Agent and oh-my-pi, not yet for CodeAF: Price (Hermes Agent: ; oh-my-pi: ), Model providers (Hermes Agent: , , , , , SpaceXSI (Grok), , Amazon Bedrock, , Moonshot AI, , , , , , , , , , , , Vercel AI Gateway, , OpenCode Console (OpenCode Zen), Alibaba (Qwen), , , Meta AI (Llama), , Microsoft Foundry (Azure AI Foundry), Nebius Token Factory (Nebius AI Studio), Novita AI, , , , , , , Command Code, , , , , , , , , , ; oh-my-pi: , , , , , SpaceXSI (Grok), , , , Moonshot AI, , , , , , , , Together AI, , , , , , , OpenCode Console (OpenCode Zen), Alibaba (Qwen), , , , Meta AI (Llama), , , Novita AI, , , , , , , , , , CoreWeave (Weights & Biases), Kilo Code, , , , , , ai&, , , Umans Code (Umans AI), Baidu AI Cloud Qianfan, , , , , , , , ), Bring your own key (Hermes Agent: ; oh-my-pi: )

Checked for oh-my-pi, not yet for CodeAF and Hermes Agent: Systems (, , , )

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.

What each can do

Select an answer to see the maker’s sentence, or what we searched.

We have not checked CodeAF’s capabilities yet. 22 capabilities are checked for at least two of these tools. 3 differ only in a limit. 12 others are checked for one tool only.

Differences only3
  • Yesthe maker documents it
  • *its limit or add-on is named under the row
  • Emptynot yet checked

Models, keys and usage

Local modelsNot yet checked: CodeAF
Not yet checked for CodeAF
Custom OpenAI-compatible endpointNot yet checked: CodeAF
Not yet checked for CodeAF
Token and cost usageNot yet checked: CodeAF, oh-my-pi
Not yet checked for CodeAF
Not yet checked for oh-my-pi

MCP, hooks, skills and subagents

MCP serversNot yet checked: CodeAF
Not yet checked for CodeAF
local and remote
local and remote
HooksNot yet checked: CodeAF
Not yet checked for CodeAF
SkillsNot yet checked: CodeAF
Not yet checked for CodeAF
SubagentsNot yet checked: CodeAF
Not yet checked for CodeAF
PluginsNot yet checked: CodeAF
Not yet checked for CodeAF
Custom commandsNot yet checked: CodeAF
Not yet checked for CodeAF

Editors, scripts and CI

Editor integrationNot yet checked: CodeAF
Not yet checked for CodeAF
ACP editors
ACP editors such as Zed
Headless modeNot yet checked: CodeAF
Not yet checked for CodeAF
JSON outputNot yet checked: CodeAF
Not yet checked for CodeAF
GitHub integrationNot yet checked: CodeAF, Hermes Agent
Not yet checked for CodeAF
Not yet checked for Hermes Agent
Off by default; uses gh

Review, steer and undo

Plan modeNot yet checked: CodeAF, Hermes Agent
Not yet checked for CodeAF
Not yet checked for Hermes Agent
Read-only modeNot yet checked: CodeAF, Hermes Agent
Not yet checked for CodeAF
Not yet checked for Hermes Agent
While planning only
Review diffsNot yet checked: CodeAF
Not yet checked for CodeAF
Needs checkpoints on
Undo file editsNot yet checked: CodeAF, oh-my-pi
Not yet checked for CodeAF
Opt-in; local and SSH only
Not yet checked for oh-my-pi

Parallel agents

Parallel sessionsNot yet checked: CodeAF, oh-my-pi
Not yet checked for CodeAF
Not yet checked for oh-my-pi
Git worktreesNot yet checked: CodeAF
Not yet checked for CodeAF

Context and memory

Project instruction filesNot yet checked: CodeAF
Not yet checked for CodeAF
Memory across sessionsNot yet checked: CodeAF
Not yet checked for CodeAF
Resume a sessionNot yet checked: CodeAF
Not yet checked for CodeAF
Browse past sessionsNot yet checked: CodeAF
Not yet checked for CodeAF

Remote and mobile control

Remote controlNot yet checked: CodeAF
Not yet checked for CodeAF
Via /collab relay
Steer from a phoneNot yet checked: CodeAF, oh-my-pi
Not yet checked for CodeAF
Unblocks Kanban workers
Not yet checked for oh-my-pi
NotificationsNot yet checked: CodeAF, oh-my-pi
Not yet checked for CodeAF
Not yet checked for oh-my-pi

Sandbox, permissions and privacy

Approval modesNot yet checked: CodeAF
Not yet checked for CodeAF
Runs in a containerNot yet checked: CodeAF, oh-my-pi
Not yet checked for CodeAF
Official Docker setup
Not yet checked for oh-my-pi

Images, web and your computer

Image inputNot yet checked: CodeAF
Not yet checked for CodeAF
Fetch URLsNot yet checked: CodeAF, Hermes Agent
Not yet checked for CodeAF
Not yet checked for Hermes Agent
Browser automationNot yet checked: CodeAF
Not yet checked for CodeAF
Computer useNot yet checked: CodeAF, Hermes Agent
Not yet checked for CodeAF
Not yet checked for Hermes Agent
Off by default; /computer turns it on
Voice inputNot yet checked: CodeAF, oh-my-pi
Not yet checked for CodeAF
Not yet checked for oh-my-pi
Not yet checked: , ,

3 capabilities are not yet checked for any of these tools and are not shown. Each answer is about the CLI agent in its column. Something the maker publishes separately, such as an editor plugin or a GitHub Action, shows as “With add-on”, even when it has its own listing here. How capabilities are checked

About these tools

CodeAF

Hermes Agent

oh-my-pi

How to read the Index score

At a glance

Index score out of 100

CodeAFNot enough data yetHermes Agent48oh-my-pi52

Mindshare HN mentions, 90 days

CodeAF0Hermes Agent84oh-my-pi120

Adoption GitHub stars, not scored

CodeAF785Hermes Agent264koh-my-pi39.3k

Release days last 90 days

CodeAF11Hermes Agent19oh-my-pi73

Platforms systems and surfaces

CodeAFNot yet checkedHermes AgentNot yet checkedoh-my-pi4

Votes can only raise a score: up to 20% of it reflects upvotes, 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. After activation, 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

Differences only
3 of 4
CodeAFAgent-Field · CLI agent
Hermes AgentCLI agent
oh-my-pican1357 · CLI agent
Interface
oh-my-pi interface
What it is
Open-Source Software factory for Open Models
Terminal agent for writing, reviewing and running code in local projects
A coding agent with the IDE wired in.
Category
CLI agent
CLI agent
CLI agent
Pricing
Starts at (billing shown)
Not yet checked
Lowest monthly plan
Not yet checked
Not yet checked
Not yet checked
Free tier
Not yet checked
Plans
Not yet checked
Bring your own key
Not yet checked
Yes
Yes
Runs on
Linux
Not yet checked
Not yet checked
Yes
Terminal
Not yet checked
Not yet checked
Yes
Windows
Not yet checked
Not yet checked
Yes
macOS
Not yet checked
Not yet checked
Yes
Models and agents
Model providers
Not yet checked
OpenAIAnthropicGoogleOpenRouterOllamaSpaceXSI (Grok)DeepSeekAmazon Bedrock
+41 more model providers
LM StudioMoonshot AIGroqZ.aiMistralFireworksMiniMaxOpenCode GoTogether AIvLLMHugging FaceAzure OpenAICerebrasVercel AI Gatewayllama.cppOpenCode Console (OpenCode Zen)Alibaba (Qwen)XiaomiNVIDIAMeta AI (Llama)LiteLLMMicrosoft Foundry (Azure AI Foundry)Nebius Token Factory (Nebius AI Studio)Novita AIDeepInfraPerplexityGMI CloudStepFunKilo CodeArcee AICommand CodeSGLangTencentUpstageClawRouterJanLocalAINous PortalActual ComputerQwenCloudRamp Router
OpenAIAnthropicGoogleOpenRouterOllamaSpaceXSI (Grok)DeepSeekAmazon Bedrock
+54 more model providers
LM StudioMoonshot AIGroqZ.aiMistralFireworksMiniMaxGitHub CopilotOpenCode GoTogether AIvLLMHugging FaceAzure OpenAICerebrasVercel AI Gatewayllama.cppOpenCode Console (OpenCode Zen)Alibaba (Qwen)XiaomiNVIDIABasetenMeta AI (Llama)Cloudflare AI GatewayLiteLLMNovita AIDeepInfraSambaNovaScalewayChutesGMI CloudInceptionStepFunSyntheticVeniceCoreWeave (Weights & Biases)Kilo CodeNanoGPTSiliconFlowCursorCommand CodeZenMuxai&Charm HyperSakana AIUmans Code (Umans AI)Baidu AI Cloud QianfanDevinModularBifrostGitLab DuoHelmcodeKiroOtariWafer Serverless
Not every provider checked yet
Models
Not yet checked
Nous PortalOpenAI CodexAnthropicOpenRouterFireworks AINovitaAIAI GatewayGLMKimiMiniMaxxAIQwen Cloud
AnthropicOpenAIOpenAI CodexGoogle GeminiGoogle VertexGoogle AntigravityxAISuperGrokDeepSeekMistralGroqCerebrasSambaNovaFireworksTogetherModularBasetenChutesDeepInfraHugging FaceNVIDIAMetaInceptionAmazon BedrockAzure OpenAISiliconFlowGMI CloudCoreWeaveSakana AICommand CodeCharm HyperStepFunHelmcodeOpenRouterSyntheticVercel AI GatewayCloudflare AI GatewayWafer ServerlessScalewayOtari
Drives these agents
Not yet checked
Not yet checked
Not yet checked
Source and activity
Source
GitHub stars
Most
Release days, last 90 days
11
19
73Most
Release days per week
Latest release, any channel
v18.22.2 18 Nov 2026
Index score
Score and rank
Not enough data yet
48 #14 Score 48.2; ranked on the unrounded score
52 #12 Score 52.1; ranked on the unrounded score
Mindshare
00 Hacker News mentions in the last 90 days
4884 Hacker News mentions in the last 90 days
52120 Hacker News mentions in the last 90 days
Adoption, not scored
55785 stars, read 17 Nov 2026
100264,230 stars, read 18 Nov 2026
8739,329 stars, read 18 Nov 2026
Votes
—Votes can only raise a score: up to 20% of it reflects upvotes, 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.
—Votes can only raise a score: up to 20% of it reflects upvotes, 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.
—Votes can only raise a score: up to 20% of it reflects upvotes, 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.
Rank history
Not ranked
First ranked 18 Nov 2026
First ranked 18 Nov 2026
Full page

Watch CodeAF vs Hermes Agent vs oh-my-pi on YouTube

More comparisons

Build your own