Skip to content
ADE Index

Claude Code CLI vs Pi vs Pydantic Deep Agents

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

This page compares the three CLI agents only. Claude Code has 4 other listings, each with its own page.

How they differ

Pick this if…

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

Checked for Claude Code CLI and Pi, not yet for Pydantic Deep Agents: Price (Claude Code CLI: ; Pi: ), Bring your own key (Claude Code CLI: ; Pi: )

Same for all 3 (1): Systems: Terminal, macOS, Windows, Linux
  • Systems: Terminal, macOS, Windows, Linux · ·

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 Pydantic Deep Agents’s capabilities yet. 20 capabilities are checked for at least two of these tools. 7 get different answers, among them Approval modes, Subagents, Plan mode and Undo file edits; 2 differ only in a limit. 17 others are checked for one tool only.

Differences only9
  • Yesthe maker documents it
  • With add-onAdd-onsomething the maker publishes that you install or run
  • No, per makerNothe maker says it does not
  • *its limit or add-on is named under the row
  • Emptynot yet checked
  • From the listingthe listing’s own facts; not one of the capabilities we check

Models, keys and usage

Named model providersFrom the listing
,,,
Listing also names: Microsoft Foundry (Azure AI Foundry)
,,,,,,,,
+22 more model providers
,,,,,,,,,,,,,,,,,,,,,
Listing also names 7 othersSpaceXSI (Grok), Z.ai, OpenCode Console (OpenCode Zen), Alibaba (Qwen), Meta AI (Llama), TypeSafe AI, Microsoft Foundry (Azure AI Foundry)
Listing also names: Google
Local modelsNot yet checked: Claude Code CLI, Pydantic Deep Agents
Not yet checked for Claude Code CLI
Not yet checked for Pydantic Deep Agents
Custom OpenAI-compatible endpointNot yet checked: Claude Code CLI, Pydantic Deep Agents
Not yet checked for Claude Code CLI
Not yet checked for Pydantic Deep Agents
Token and cost usageNot yet checked: Pydantic Deep Agents
Token view for API users
Not yet checked for Pydantic Deep Agents

MCP, hooks, skills and subagents

MCP serversNot yet checked: Pydantic Deep Agents
local and remote
local and remote
Not yet checked for Pydantic Deep Agents
HooksNot yet checked: Pydantic Deep Agents
Not yet checked for Pydantic Deep Agents
SkillsNot yet checked: Pydantic Deep Agents
Not yet checked for Pydantic Deep Agents
SubagentsNot yet checked: Pydantic Deep Agents
Not built in; Subagent example
Not yet checked for Pydantic Deep Agents
PluginsNot yet checked: Pydantic Deep Agents
Not yet checked for Pydantic Deep Agents
Custom commandsNot yet checked: Pydantic Deep Agents
Not yet checked for Pydantic Deep Agents

Editors, scripts and CI

Editor integrationNot yet checked: Pi, Pydantic Deep Agents
VS Code extension or JetBrains plugin
Not yet checked for Pi
Not yet checked for Pydantic Deep Agents
Headless modeNot yet checked: Pydantic Deep Agents
Not yet checked for Pydantic Deep Agents
JSON outputNot yet checked: Pydantic Deep Agents
Not yet checked for Pydantic Deep Agents
GitHub integrationNot yet checked: Pi, Pydantic Deep Agents
Claude Code GitHub Action
Not yet checked for Pi
Not yet checked for Pydantic Deep Agents
Commit attribution controlNot yet checked: Pi, Pydantic Deep Agents
Not yet checked for Pi
Not yet checked for Pydantic Deep Agents

Review, steer and undo

Plan modeNot yet checked: Pydantic Deep Agents
Not built in; Plan Mode example
Not yet checked for Pydantic Deep Agents
Read-only modeNot yet checked: Pydantic Deep Agents
Through plan mode
Not built in; Plan Mode example
Not yet checked for Pydantic Deep Agents
Review diffsNot yet checked: Pi, Pydantic Deep Agents
Not yet checked for Pi
Not yet checked for Pydantic Deep Agents
Undo file editsNot yet checked: Pydantic Deep Agents
Maker's git-checkpoint example
Not yet checked for Pydantic Deep Agents

Parallel agents

Parallel sessionsNot yet checked: Pi, Pydantic Deep Agents
Not yet checked for Pi
Not yet checked for Pydantic Deep Agents
Git worktreesNot yet checked: Pi, Pydantic Deep Agents
Not yet checked for Pi
Not yet checked for Pydantic Deep Agents

Context and memory

Project instruction filesNot yet checked: Pydantic Deep Agents
Not yet checked for Pydantic Deep Agents
Memory across sessionsNot yet checked: Pi, Pydantic Deep Agents
Not yet checked for Pi
Not yet checked for Pydantic Deep Agents
Resume a sessionNot yet checked: Pydantic Deep Agents
Not yet checked for Pydantic Deep Agents
Browse past sessionsNot yet checked: Pydantic Deep Agents
Not yet checked for Pydantic Deep Agents

Remote and mobile control

Remote controlNot yet checked: Pi, Pydantic Deep Agents
Needs a Claude plan, not an API key
Not yet checked for Pi
Not yet checked for Pydantic Deep Agents
Steer from a phoneNot yet checked: Pi, Pydantic Deep Agents
Needs a Claude plan, not an API key
Not yet checked for Pi
Not yet checked for Pydantic Deep Agents
NotificationsNot yet checked: Pydantic Deep Agents
Depends on the terminal
Maker's notify example
Not yet checked for Pydantic Deep Agents

Sandbox, permissions and privacy

OS-level sandboxNot yet checked: Pydantic Deep Agents
Not on native Windows
Gondolin micro-VM example
Not yet checked for Pydantic Deep Agents
Approval modesNot yet checked: Pydantic Deep Agents
Not yet checked for Pydantic Deep Agents
Runs in a containerNot yet checked: Claude Code CLI, Pydantic Deep Agents
Not yet checked for Claude Code CLI
The repo's Docker recipe
Not yet checked for Pydantic Deep Agents
Telemetry opt-outNot yet checked: Pydantic Deep Agents
Not yet checked for Pydantic Deep Agents

Images, web and your computer

Image inputNot yet checked: Pydantic Deep Agents
Needs a compatible terminal
Not yet checked for Pydantic Deep Agents
Fetch URLsNot yet checked: Pi, Pydantic Deep Agents
Not yet checked for Pi
Not yet checked for Pydantic Deep Agents
Browser automationNot yet checked: Pi, Pydantic Deep Agents
Claude in Chrome extension
Not yet checked for Pi
Not yet checked for Pydantic Deep Agents
Computer useNot yet checked: Pi, Pydantic Deep Agents
macOS only; Pro, Max or Ultra plan
Not yet checked for Pi
Not yet checked for Pydantic Deep Agents
Voice inputNot yet checked: Pi, Pydantic Deep Agents
Claude.ai sign-in; no cloud or SSH
Not yet checked for Pi
Not yet checked for Pydantic Deep Agents
Not yet checked: , ,

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

Claude Code CLI

Pi

Pydantic Deep Agents

How to read the Index score

At a glance

Index score out of 100

Claude Code CLI92Pi78Pydantic Deep AgentsNot enough data yet

Mindshare HN mentions, 90 days

Claude Code CLI4,602Pi1,310Pydantic Deep Agents0

Adoption GitHub stars, not scored

Claude Code CLI156kPi123kPydantic Deep Agents1.1k

Release days last 90 days

Claude Code CLI57Pi19Pydantic Deep Agents2

Lowest monthly plan billed monthly, lower is cheaper

Claude Code CLI$20/moPiNot yet checkedPydantic Deep AgentsNot yet checked

Platforms systems and surfaces

Claude Code CLI5Pi4Pydantic Deep Agents4

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
Claude Code CLIAnthropic · CLI agent
PiEarendil Works · CLI agent
Pydantic Deep AgentsVstorm · CLI agent
Interface
Terminal session listing file searches and reads while tests run
pi startup listing loaded context, skills and extensions, then reading docs and running bash
What it is
Terminal coding tool that executes routine tasks and handles git workflows
Minimal, extensible agent harness that you can make your own
Open-source, self-hosted Claude Code - a terminal AI assistant and the Python framework behind it.
Category
CLI agentClaude Code family
CLI agent
CLI agent
Pricing
Starts at (billing shown)
Not yet checked
Lowest monthly plan
Not yet checked
Not yet checked
Free tier
Not yet checked
Not yet checked
Plans
Not yet checked
Bring your own key
Yes
Yes
Not yet checked
Runs on
Linux
Yes
Yes
Yes
Terminal
Yes
Yes
Yes
Web
Yes
Not yet checked
Not yet checked
Windows
Yes
Yes
Yes
macOS
Yes
Yes
Yes
Models and agents
Drives these agents
Not yet checked
Not yet checked
Not yet checked
Source and activity
Source
GitHub stars
Most
Release days, last 90 days
57Most
19
2
Release days per week
Latest release, any channel
v2.1.327 17 Nov 2026
v1.5.2 10 Nov 2026
0.3.50 6 Oct 2026
Index score
Score and rank
92 #1 Score 91.6; ranked on the unrounded score
78 #4 Score 77.9; ranked on the unrounded score
Not enough data yet
Mindshare
924,602 Hacker News mentions in the last 90 days
781,310 Hacker News mentions in the last 90 days
00 Hacker News mentions in the last 90 days
Adoption, not scored
98156,056 stars, read 18 Nov 2026
96122,575 stars, read 18 Nov 2026
581,120 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
First ranked 18 Nov 2026
First ranked 18 Nov 2026
Not ranked
Full page

Watch Claude Code CLI vs Pi vs Pydantic Deep Agents on YouTube

More comparisons

Build your own