Skip to content
ADE Index

AgentConnect vs CodeMachine-CLI vs Thrum vs zeroshot

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

How they differ

Pick this if…

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

Sourced for AgentConnect, Thrum and zeroshot, not yet checked for CodeMachine-CLI: Price (AgentConnect: ; Thrum: ; zeroshot: )

Sourced for zeroshot, not yet checked for AgentConnect, CodeMachine-CLI and Thrum: Model providers (, , , Amazon Bedrock, Microsoft Foundry (Azure AI Foundry)), Bring your own key (), Agents it runs ()

Not yet checked for any of these tools: editors and systems.

Provider names use the same listing as each tool page. Dotted values open their quote. A capability not shown is not yet sourced; the tool may still have it.

About these tools

AgentConnect

CodeMachine-CLI

Thrum

zeroshot

How to read the Index score

At a glance

Index score out of 100

AgentConnect21CodeMachine-CLINot enough data yetThrum15zeroshot17

Mindshare HN mentions, 90 days

AgentConnect6CodeMachine-CLI0Thrum3zeroshot4

Adoption GitHub stars, not scored

AgentConnect1.5kCodeMachine-CLI2.5kThrumNo public repositoryzeroshot2.2k

Release days last 90 days

AgentConnect32CodeMachine-CLI0ThrumNot yet checkedzeroshot41

Lowest monthly plan billed monthly, lower is cheaper

AgentConnectNot yet checkedCodeMachine-CLINot yet checkedThrum$15.00/monthzeroshotNot yet 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

4 of 4
AgentConnectagentconnect-md · Agent orchestrator
CodeMachine-CLImoaz 👾 · Agent orchestrator
ThrumAgent orchestrator
zeroshotThe Open Engine Company · Agent orchestrator
Interface
thrum interface shown on the official site
What it is
Bring multiple coding agents into team workflows through agent mentions
Orchestrate coding agents through repeatable, long-running workflows
Cross-tool messaging for Claude Code, Codex, Cursor and other coding agents
Coding-agent graph harness with separate review and test agents
Category
Agent orchestrator
Agent orchestrator
Agent orchestrator
Agent orchestrator
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
Not yet checked
Not yet checked
Yes
Runs on
Models and agents
Model providers
Not yet checked
Not yet checked
Not yet checked
AnthropicOpenAIOpenRouterAmazon BedrockMicrosoft Foundry (Azure AI Foundry)
Models
Not yet checked
Not yet checked
Not yet checked
CodexOpenAIAnthropicOpenRouter
Drives these agents
Not yet checked
Not yet checked
Not yet checked
Codex
Source and activity
Source
Not yet checked
GitHub stars
Most
No public repository
Release days, last 90 days
32
0
Not yet checked
41Most
Release days per week
Not yet checked
Latest release, any channel
v2.16.0 18 Nov 2026
v0.8.0 2 Feb 2026
Not yet checked
v16.1.0 18 Nov 2026
Index score
Score and rank
21 #70 Score 21.1; ranked on the unrounded score
Not enough data yet
15 #91 Score 15.1; ranked on the unrounded score
17 #80 Score 17.5; ranked on the unrounded score
Mindshare
216 Hacker News mentions in the last 90 days
00 Hacker News mentions in the last 90 days
153 Hacker News mentions in the last 90 days
174 Hacker News mentions in the last 90 days
Adoption, not scored
601,543 stars, read 18 Nov 2026
642,517 stars, read 18 Nov 2026
No public repository
632,190 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.
—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
Not ranked
First ranked 18 Nov 2026
First ranked 18 Nov 2026
Full page

Watch AgentConnect vs CodeMachine-CLI vs Thrum vs zeroshot on YouTube

More comparisons

Build your own