Kimi CLI (legacy Python) has been superseded by Kimi Code CLI: Kimi CLI (Python) has been replaced by **Kimi Code CLI**, the next-generation terminal AI agent from the same team.github.com
Paraphrased from each maker’s own description. Select a line for the quote.
Checked for cecli, Hermes Agent and Pi, not yet for Kimi CLI (legacy Python): Bring your own key (cecli: ; Hermes Agent: ; Pi: )
Checked for cecli, Kimi CLI (legacy Python) and Pi, not yet for Hermes Agent: Systems (cecli: , ; Kimi CLI (legacy Python): ,, ; Pi: ,,, )
Same for all 4 (1): Price: Free (open source)
Price: Free (open source) · · ·
Not yet checked for any of these tools: agents it runs.
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 Kimi CLI (legacy Python)’s capabilities yet. 19 capabilities are checked for at least two of these tools. 4 get different answers: Approval modes, Subagents, Undo file edits and Notifications; 2 differ only in a limit. 14 others are checked for one tool only.
Listing also names 14 othersSpaceXSI (Grok), OpenCode Console (OpenCode Zen), Alibaba (Qwen), Cloudflare Workers AI, Meta AI (Llama), Microsoft Foundry (Azure AI Foundry), Nebius Token Factory (Nebius AI Studio), OVHcloud AI Endpoints, CoreWeave (Weights & Biases), NanoGPT, Helicone AI Gateway, v0 API, Apertis (Stima API), Public AI
Hermes Agent
,,,,,,,,+30 more model providers
,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
Listing also names 11 othersSpaceXSI (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
Listing also names 7 othersSpaceXSI (Grok), Z.ai, OpenCode Console (OpenCode Zen), Alibaba (Qwen), Meta AI (Llama), TypeSafe AI, Microsoft Foundry (Azure AI Foundry)
Local modelsNot yet checked: cecli, Kimi CLI (legacy Python)
Not yet checked for cecli
Not yet checked for Kimi CLI (legacy Python)
Custom OpenAI-compatible endpointNot yet checked: cecli, Kimi CLI (legacy Python)
Not yet checked for cecli
Not yet checked for Kimi CLI (legacy Python)
Token and cost usageNot yet checked: cecli, Kimi CLI (legacy Python)
Not yet checked for cecli
Not yet checked for Kimi CLI (legacy Python)
MCP, hooks, skills and subagents
MCP serversNot yet checked: cecli, Kimi CLI (legacy Python)
Not yet checked for cecli
local and remote
Not yet checked for Kimi CLI (legacy Python)
local and remote
HooksNot yet checked: Kimi CLI (legacy Python)
Not yet checked for Kimi CLI (legacy Python)
SkillsNot yet checked: cecli, Kimi CLI (legacy Python)
Not yet checked for cecli
Not yet checked for Kimi CLI (legacy Python)
SubagentsNot yet checked: Kimi CLI (legacy Python)
Not yet checked for Kimi CLI (legacy Python)
*Not built in; Subagent example
Pi Not built in; Subagent example
PluginsNot yet checked: Kimi CLI (legacy Python)
Not yet checked for Kimi CLI (legacy Python)
Custom commandsNot yet checked: cecli, Kimi CLI (legacy Python)
Not yet checked for cecli
Not yet checked for Kimi CLI (legacy Python)
Editors, scripts and CI
Editor integrationNot yet checked: cecli, Kimi CLI (legacy Python), Pi
Not yet checked for cecli
*ACP editors
Not yet checked for Kimi CLI (legacy Python)
Not yet checked for Pi
Hermes Agent ACP editors
Headless modeNot yet checked: cecli, Kimi CLI (legacy Python)
Not yet checked for cecli
Not yet checked for Kimi CLI (legacy Python)
JSON outputNot yet checked: cecli, Kimi CLI (legacy Python)
Not yet checked for cecli
Not yet checked for Kimi CLI (legacy Python)
Review, steer and undo
Plan modeNot yet checked: cecli, Hermes Agent, Kimi CLI (legacy Python)
Editors, scripts and CI Editor integration, Headless mode, JSON output, GitHub integration, Commit attribution control
Review, steer and undo Plan mode, Read-only mode, Review diffs, Undo file edits
Parallel agents Parallel sessions, Git worktrees
Context and memory Project instruction files, Memory across sessions, Resume a session, Browse past sessions
Remote and mobile control Remote control, Steer from a phone, Notifications
Sandbox, permissions and privacy OS-level sandbox, Approval modes, Runs in a container, Telemetry opt-out
Images, web and your computer Image input, Web search, Fetch URLs, Browser automation, Computer use, Voice input
We have not checked these yet. They may or may not be supported.
,
14 capabilities not yet checked for Pi
Editors, scripts and CI Editor integration, GitHub integration, Commit attribution control
Review, steer and undo Review diffs
Parallel agents Parallel sessions, Git worktrees
Context and memory Memory across sessions
Remote and mobile control Remote control, Steer from a phone
Images, web and your computer Web search, Fetch URLs, Browser automation, Computer use, Voice input
We have not checked these yet. They may or may not be supported.
4 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
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
—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.
—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.