Access
Install
npm install --global '@yylo/cli@latest'
vs Foreloop
vs Factory
vs Devin
vs OpenHands
vs Codegen
vs Jules
vs Omnara
vs HumanLayerShowcase
Try itExperimental
See what an agent can do with YYLO before you ever sign up. Pick a story: recorded sessions replay real probe-harness transcripts; commands tagged live-capable can re-run against the real endpoint from our edge, right now (▶ run live — the exact same request, live and recorded lines always labeled); sandboxed self-drive sessions are designed and gated (docs/TRY-IT.md).
$npm view @yylo/cli name version binrecorded session — replayed, not liveVerified integrations
Connections to other tracked products — hover a chip for the verbatim evidence quote behind it.
By theme — the product's score on each story themeBy theme
Agenticness — how well agents can access and operate the productAgenticnessevidence →
How well agents can access and operate the product
Automation depth — how much of the product can run unattendedAutomation depthevidence →
How much of the product can run unattended
Autonomous implementation — end-to-end implementation by the agent — multi-file changes, task completionAutonomous implementationevidence →
End-to-end implementation by the agent — multi-file changes, task completion
Human oversight — keeping a human in the loop — approvals, checkpoints, interruptsHuman oversightevidence →
Keeping a human in the loop — approvals, checkpoints, interrupts
Intent to spec — stories about intent to spec in this arenaIntent to specevidence →
Stories about intent to spec in this arena
Openness — open source, data portability, and self-hosting storiesOpennessevidence →
Open source, data portability, and self-hosting stories
Pricing limits — free-tier ceilings, usage caps, and rate limits before you have to payPricing limitsevidence →
Free-tier ceilings, usage caps, and rate limits before you have to pay
Privacy posture — data-handling and privacy storiesPrivacy postureevidence →
Data-handling and privacy stories
Repo integration — stories about repo integration in this arenaRepo integrationevidence →
Stories about repo integration in this arena
Review quality gates — quality gates on changes — review flow, required checks, merge protectionReview quality gatesevidence →
Quality gates on changes — review flow, required checks, merge protection
Scale parallelism — running many jobs at once — concurrency, fleets, queueingScale parallelismevidence →
Running many jobs at once — concurrency, fleets, queueing
Story verdicts — every judged story with its evidenceStory verdicts
What’s free: 4 free · 0 paid · 0 enterprise · 24 not stated in evidence
Follow the green: where the map greys out is where YYLO stops today. ✓ full · ~ partial · ! disputed · — none · n/a not applicable.
Agenticness — how well agents can access and operate the productAgenticness
How well agents can access and operate the product
API surface
Drive the product through a documented public API
~5/10
unlocks → Webhooks · Official SDKs · MCP server · Machine-readable spec · Versioning policy · Have an agent automatically generate and run tests to validate its own code changes before proposing them · Go from a mockup or design to a working implementation without an engineering handoff · Send follow-up instructions to an active agent session to steer its work without restarting · Have an agent safely execute code and install dependencies inside an isolated sandbox · Add a context file describing my codebase conventions so agents generate more relevant plans and code · Connect issue trackers like Jira, Linear, ClickUp, or Monday.com so agents can manage tickets directly · Connect a GitHub repository so an agent can access the code and open pull requests against it · Grant an agent access to my repositories with a one-click install, without complex setup
Subscribe to events via webhooks
—0/10
Build against official SDKs
—0/10
Issue scoped/least-privilege API credentials for an agent
n/an/a
Connect an agent via an official MCP server
—–
Download a machine-readable API spec (OpenAPI or equivalent)
—0/10
Rely on versioned APIs with a documented deprecation policy
—0/10
Test against a sandbox environment without touching production data
✓7/10
Explore an interactive API reference with runnable examples
—0/10
Docs for agents
Point an agent at llms.txt or agent-oriented docs
—0/10
Agentic features
Delegate tasks to a built-in AI assistant inside the product
~4/10
unlocks → NL commands · MCP client · AI insights
Operate the product with natural-language commands
—0/10
Plug MCP servers into this product so it can use their tools
—–
Get AI-generated insights and suggestions from my data inside the product
—0/10
Set up automations that run autonomously in the background
~7/10
Automation depth — how much of the product can run unattendedAutomation depth
How much of the product can run unattended
Autonomous implementation — end-to-end implementation by the agent — multi-file changes, task completionAutonomous implementation
End-to-end implementation by the agent — multi-file changes, task completion
End to end feature delivery
Have an agent automatically clone the repo, install dependencies, and configure its own working environment
~7/10
Interactive takeover
Have an agent safely execute code and install dependencies inside an isolated sandbox
—0/10
Human oversight — keeping a human in the loop — approvals, checkpoints, interruptsHuman oversight
Keeping a human in the loop — approvals, checkpoints, interrupts
Approval controls
Model control
Intent to spec — stories about intent to spec in this arenaIntent to spec
Stories about intent to spec in this arena
Natural language task intake
Plan approval
Assign a coding task to an agent directly from an existing issue or ticket
~6/10
Openness — open source, data portability, and self-hosting storiesOpenness
Open source, data portability, and self-hosting stories
Pricing limits — free-tier ceilings, usage caps, and rate limits before you have to payPricing limits
Free-tier ceilings, usage caps, and rate limits before you have to pay
Privacy posture — data-handling and privacy storiesPrivacy posture
Data-handling and privacy stories
Repo integration — stories about repo integration in this arenaRepo integration
Stories about repo integration in this arena
Review quality gates — quality gates on changes — review flow, required checks, merge protectionReview quality gates
Quality gates on changes — review flow, required checks, merge protection
Ci remediation
Diff review
Pr review automation
Readiness checks
Have security alerts automatically validated and remediated with an opened pull request
n/an/a
Scale parallelism — running many jobs at once — concurrency, fleets, queueingScale parallelism
Running many jobs at once — concurrency, fleets, queueing
Concurrent execution
Deployment flexibility
Run an agent headlessly inside CI/CD pipelines and shell scripts
~6/10
Sorted by importance (agentic first) (high → low) · 73/73 stories · click a row’s chevron for the rationale and evidence
Drive the product through a documented public API G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | partial | 5/10 | Tprobed | |
Delegate tasks to a built-in AI assistant inside the product G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | partial | 4/10 | Cclaimed | |
Connect an agent via an official MCP server G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | none | untested | none yet | |
Plug MCP servers into this product so it can use their tools G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | none | untested | none yet | |
Use an official CLI G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | full | 8/10 | Tprobed | |
Run the product headlessly / in CI for automation G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | full | 7/10 | Tprobed | |
Set up automations that run autonomously in the background G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | partial | 7/10 | Cclaimed | |
Build against official SDKs G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Download a machine-readable API spec (OpenAPI or equivalent) G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Explore an interactive API reference with runnable examples G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Get AI-generated insights and suggestions from my data inside the product G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Operate the product with natural-language commands G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Point an agent at llms.txt or agent-oriented docs G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Rely on versioned APIs with a documented deprecation policy G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Subscribe to events via webhooks G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Issue scoped/least-privilege API credentials for an agent G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | n/a | untested | none yet | |
Test against a sandbox environment without touching production data G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 1 | full | 7/10 | Cclaimed | |
Self-host the core product G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 3 | fullfree | 8/10 | Tprobed | |
Assign a coding task to an agent directly from an existing issue or ticket C Ticket driven tasking | developer | Intent to spec — stories about intent to spec in this arenaIntent to spec | 3 | partial | 6/10 | Cclaimed | |
Describe a feature or bug in plain language and have it automatically turned into a scoped implementation task C Natural language task intake | developer | Intent to spec — stories about intent to spec in this arenaIntent to spec | 3 | partial | 6/10 | Cclaimed | |
Run many agent tasks concurrently to scale delivery throughput C Concurrent execution | engineering-lead | Scale parallelism — running many jobs at once — concurrency, fleets, queueingScale parallelism | 3 | partial | 6/10 | Cclaimed | |
Define rules that trigger actions automatically on events G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 3 | partial | 5/10 | Cclaimed | |
Have an agent autonomously diagnose and fix a reported bug C End to end feature delivery | developer | Autonomous implementation — end-to-end implementation by the agent — multi-file changes, task completionAutonomous implementation | 3 | partial | 5/10 | Cclaimed | |
Have an agent implement a requested feature end-to-end, including writing tests C End to end feature delivery | developer | Autonomous implementation — end-to-end implementation by the agent — multi-file changes, task completionAutonomous implementation | 3 | partial | 5/10 | Cclaimed | |
Export all of my data in open formats and leave G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 3 | partialfree | 4/10 | Tprobed | |
Watch what a running agent is doing in real time, including its current status C Visibility monitoring | developer | Human oversight — keeping a human in the loop — approvals, checkpoints, interruptsHuman oversight | 3 | partial | 4/10 | Cclaimed | |
Connect a GitHub repository so an agent can access the code and open pull requests against it C Version control integration | developer | Repo integration — stories about repo integration in this arenaRepo integration | 3 | none | 0/10 | ||
Connect issue trackers like Jira, Linear, ClickUp, or Monday.com so agents can manage tickets directly C Project management integration | product-manager | Repo integration — stories about repo integration in this arenaRepo integration | 3 | none | 0/10 | ||
Have an agent safely execute code and install dependencies inside an isolated sandbox C Sandbox execution | developer | Autonomous implementation — end-to-end implementation by the agent — multi-file changes, task completionAutonomous implementation | 3 | none | 0/10 | ||
Have every pull request automatically reviewed with AI-generated inline comments C Pr review automation | engineering-lead | Review quality gates — quality gates on changes — review flow, required checks, merge protectionReview quality gates | 3 | none | 0/10 | ||
Have failed CI workflows automatically diagnosed and fixed with a proposed pull request C Ci remediation | engineering-lead | Review quality gates — quality gates on changes — review flow, required checks, merge protectionReview quality gates | 3 | none | 0/10 | ||
Review a diff of an agent's changes and approve it before it becomes a pull request C Diff review | developer | Review quality gates — quality gates on changes — review flow, required checks, merge protectionReview quality gates | 3 | none | 0/10 | ||
Review and approve an agent's implementation plan before any code changes are made C Plan approval | developer | Intent to spec — stories about intent to spec in this arenaIntent to spec | 3 | none | 0/10 | ||
Add a context file describing my codebase conventions so agents generate more relevant plans and code C Knowledge context | developer | Repo integration — stories about repo integration in this arenaRepo integration | 3 | none | untested | none yet | |
Prevent my data from being used to train AI models G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 3 | n/a | untested | none yet | |
Set tiered autonomy levels controlling what an agent can do without manual confirmation C Approval controls | engineering-lead | Human oversight — keeping a human in the loop — approvals, checkpoints, interruptsHuman oversight | 3 | none | untested | none yet | |
Perform bulk operations across many items at once G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 2 | full | 8/10 | Tprobed | |
Read the product's source under an open license G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 2 | fullfree | 8/10 | Tprobed | |
Have an agent automatically clone the repo, install dependencies, and configure its own working environment C Environment setup | developer | Autonomous implementation — end-to-end implementation by the agent — multi-file changes, task completionAutonomous implementation | 2 | partial | 7/10 | Tprobed | |
Run an agent headlessly inside CI/CD pipelines and shell scripts C Headless automation | developer | Scale parallelism — running many jobs at once — concurrency, fleets, queueingScale parallelism | 2 | partial | 6/10 | Tprobed | |
Get notified when an agent completes a task or needs my input C Visibility monitoring | developer | Human oversight — keeping a human in the loop — approvals, checkpoints, interruptsHuman oversight | 2 | partial | 5/10 | Cclaimed | |
Schedule recurring jobs or workflows G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 2 | partial | 5/10 | Cclaimed | |
Self-host agent infrastructure locally, in containers, or on my own VMs C Deployment flexibility | engineering-lead | Scale parallelism — running many jobs at once — concurrency, fleets, queueingScale parallelism | 2 | partialfree | 5/10 | Tprobed | |
Approve a task's scope and contract before an agent is allowed to modify the repository C Plan approval | engineering-lead | Intent to spec — stories about intent to spec in this arenaIntent to spec | 2 | partial | 4/10 | Cclaimed | |
Convert user feedback submissions into structured tasks with proposed scope C Natural language task intake | product-manager | Intent to spec — stories about intent to spec in this arenaIntent to spec | 2 | partial | 4/10 | Tprobed | |
Run a readiness report that evaluates how ready my repository is for autonomous agents C Readiness checks | engineering-lead | Review quality gates — quality gates on changes — review flow, required checks, merge protectionReview quality gates | 2 | partial | 4/10 | Cclaimed | |
Take over an in-progress agent task in my editor, terminal, or browser to finish or redirect the work C Interactive takeover | developer | Autonomous implementation — end-to-end implementation by the agent — multi-file changes, task completionAutonomous implementation | 2 | partial | 4/10 | Cclaimed | |
Bring my own LLM or API key so agents run on the model of my choice C Model flexibility | engineering-lead | Pricing limits — free-tier ceilings, usage caps, and rate limits before you have to payPricing limits | 2 | none | 0/10 | ||
Choose where my data is stored (region/residency) G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 2 | n/a | 0/10 | ||
Configure an agent to auto-approve all its actions instead of confirming each one C Approval controls | developer | Human oversight — keeping a human in the loop — approvals, checkpoints, interruptsHuman oversight | 2 | none | 0/10 | ||
Configure an agent to automatically open a pull request when its task completes C Diff review | developer | Review quality gates — quality gates on changes — review flow, required checks, merge protectionReview quality gates | 2 | none | 0/10 | ||
Create agent sessions on behalf of other users in my organization C Concurrent execution | engineering-lead | Scale parallelism — running many jobs at once — concurrency, fleets, queueingScale parallelism | 2 | n/a | 0/10 | ||
Do everything through the API that I can do in the UI G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 2 | n/a | 0/10 | ||
Go from a mockup or design to a working implementation without an engineering handoff C End to end feature delivery | product-manager | Autonomous implementation — end-to-end implementation by the agent — multi-file changes, task completionAutonomous implementation | 2 | none | 0/10 | ||
Grant an agent access to my repositories with a one-click install, without complex setup C Version control integration | developer | Repo integration — stories about repo integration in this arenaRepo integration | 2 | none | 0/10 | ||
Have an agent automatically generate and run tests to validate its own code changes before proposing them C End to end feature delivery | ai-native user | Autonomous implementation — end-to-end implementation by the agent — multi-file changes, task completionAutonomous implementation | 2 | none | 0/10 | ||
Have each task prompt automatically routed to the most suitable underlying model C Model control | ai-native user | Human oversight — keeping a human in the loop — approvals, checkpoints, interruptsHuman oversight | 2 | none | 0/10 | ||
Have incoming issues automatically triaged with severity suggested and routed to the right owner C Pr review automation | ai-native user | Review quality gates — quality gates on changes — review flow, required checks, merge protectionReview quality gates | 2 | none | 0/10 | ||
Have security alerts automatically validated and remediated with an opened pull request C Security remediation | engineering-lead | Review quality gates — quality gates on changes — review flow, required checks, merge protectionReview quality gates | 2 | n/a | 0/10 | ||
License an enterprise deployment with SSO and commercial support for organization-wide rollout G Enterprise licensing | engineering-lead | Pricing limits — free-tier ceilings, usage caps, and rate limits before you have to payPricing limits | 2 | none | 0/10 | ||
See and manage plan-based daily task and concurrency limits for agent workflows G Usage quotas | engineering-lead | Pricing limits — free-tier ceilings, usage caps, and rate limits before you have to payPricing limits | 2 | n/a | 0/10 | ||
Send follow-up instructions to an active agent session to steer its work without restarting C Interactive takeover | developer | Autonomous implementation — end-to-end implementation by the agent — multi-file changes, task completionAutonomous implementation | 2 | none | 0/10 | ||
Trigger an agent from CI/CD pipelines to fix a broken build or failing test C Ci remediation | developer | Review quality gates — quality gates on changes — review flow, required checks, merge protectionReview quality gates | 2 | none | 0/10 | ||
Attach a marked-up screenshot or mockup to a task so the agent implements the correct visual change C Natural language task intake | developer | Intent to spec — stories about intent to spec in this arenaIntent to spec | 2 | n/a | untested | none yet | |
Control data retention and deletion G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 2 | none | untested | none yet | |
Opt out of telemetry and usage tracking G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 2 | none | untested | none yet | |
Tag an agent in a chat thread to discuss and delegate a bug or task C Chat integration | developer | Repo integration — stories about repo integration in this arenaRepo integration | 2 | n/a | untested | none yet | |
Use a managed cloud offering to run agents without operating my own backend infrastructure C Deployment flexibility | developer | Scale parallelism — running many jobs at once — concurrency, fleets, queueingScale parallelism | 2 | n/a | untested | none yet | |
Switch away from automatic model selection to a specific model of my choice C Model control | engineering-lead | Human oversight — keeping a human in the loop — approvals, checkpoints, interruptsHuman oversight | 1 | partial | 5/10 | Cclaimed | |
Version, review, and roll back my automations G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 1 | partial | 5/10 | Cclaimed | |
Approve key agent decisions from my phone while agents continue working C Approval controls | product-manager | Human oversight — keeping a human in the loop — approvals, checkpoints, interruptsHuman oversight | 1 | none | 0/10 | ||
Automatically fix failing agent-readiness criteria in my repository C Readiness checks | engineering-lead | Review quality gates — quality gates on changes — review flow, required checks, merge protectionReview quality gates | 1 | none | 0/10 | ||
Query generated documentation for any public or private repository C Knowledge context | developer | Repo integration — stories about repo integration in this arenaRepo integration | 1 | n/a | untested | none yet |
Opportunities — the stories that would move this product's scores, from its own judged verdictsOpportunitiestop 8 of 56 stories with headroom
What would move YYLO’s scores — derived from its own judged verdicts, biggest headroom first. Each line quotes what the judge found missing; shipping it (or evidencing it publicly) is the fix.
Agenticness — how well agents can access and operate the productPlug MCP servers into this product so it can use their tools
nonemoves agent-readyimpact 45
YYLO's docs describe orchestrating coding agents, ledgers, workflows, and an 'open-standard path' for skills, but no evidence anywhere mentions MCP servers or a mechanism to plug in MCP tools for the agents it orchestrates.
Agenticness — how well agents can access and operate the productConnect an agent via an official MCP server
nonemoves agent-readyimpact 45
YYLO is a CLI orchestrator for coding agents/workflows, and as such platform-type product it could plausibly ship an official MCP server for other agents to connect to, but no evidence pack item mentions MCP at all (only 'open-standard' skills installation, ledger, workflow-runner, etc.).
Intent to spec — stories about intent to spec in this arenaReview and approve an agent's implementation plan before any code changes are made
nonemoves PA Scoreimpact 30
Evidence describes YYLO's task lifecycle (init, start, preflight read-only, finish queuing a candidate, merge land) but nothing indicates the agent produces an implementation plan that a developer reviews and approves before any code is written — preflight/checks occur on already-produced work, not a pre-code plan gate.
Review quality gates — quality gates on changes — review flow, required checks, merge protectionHave every pull request automatically reviewed with AI-generated inline comments
nonemoves PA Scoreimpact 30
YYLO's own docs describe it as a CLI orchestrator for coding-agent tasks, workflows, and receipt-backed merges — not a PR-review tool.
Review quality gates — quality gates on changes — review flow, required checks, merge protectionHave failed CI workflows automatically diagnosed and fixed with a proposed pull request
nonemoves PA Scoreimpact 30
YYLO is a CLI orchestrator for coding agents/workflows with kanban, ledger, and merge tooling, but nothing in the evidence pack mentions CI workflow failure detection, diagnosis, or auto-generating a fix PR from a failing CI run.
Repo integration — stories about repo integration in this arenaAdd a context file describing my codebase conventions so agents generate more relevant plans and code
nonemoves PA Scoreimpact 30
The evidence pack covers task orchestration, kanban ledgers, merge protections, and workflow runners, but nowhere describes a context/conventions file that agents read to generate more relevant plans or code.
Repo integration — stories about repo integration in this arenaConnect a GitHub repository so an agent can access the code and open pull requests against it
nonemoves PA Scoreimpact 30
Evidence shows YYLO operates on local git worktrees/branches and has an internal 'merge land' step, and can pull GitHub issues into its kanban, but there is no evidence of connecting a GitHub repository as a remote and having the agent open pull requests against it — the merge feature explicitly stays local/internal with no GitHub PR API integration mentioned.
Review quality gates — quality gates on changes — review flow, required checks, merge protectionReview a diff of an agent's changes and approve it before it becomes a pull request
nonemoves PA Scoreimpact 30
Docs describe worktrees, candidate branches, and a 'merge land' step, but nowhere is there evidence of a diff-review UI or an explicit developer approval gate before a pull request is opened; in fact merge is described as launching 'no models, no reviewers' and reviews are called 'explicit project checks outside merge', with no PR-creation flow documented at all.
Showing the top 8 of 56 — every none/partial verdict in the story verdicts table is headroom.
Think a verdict is wrong? Every verdicts-table row has a Flag link — see the methodology.
Coverage map — which docs area, API section, or community source covers which judged storiesCoverage map5 surfaces · 28 covered stories
Where the cited evidence behind each covered verdict came from — the same citations the verdicts table shows, no extra judging.
docs25 stories
- Run the product headlessly / in CI for automation
- Use an official CLI
- Drive the product through a documented public API
- Set up automations that run autonomously in the background
- Delegate tasks to a built-in AI assistant inside the product
- Test against a sandbox environment without touching production data
- Perform bulk operations across many items at once
- Define rules that trigger actions automatically on events
- Schedule recurring jobs or workflows
- Version, review, and roll back my automations
- Have an agent autonomously diagnose and fix a reported bug
- Have an agent implement a requested feature end-to-end, including writing tests
- Have an agent automatically clone the repo, install dependencies, and configure its own working environment
- Take over an in-progress agent task in my editor, terminal, or browser to finish or redirect the work
- Switch away from automatic model selection to a specific model of my choice
- Watch what a running agent is doing in real time, including its current status
- Get notified when an agent completes a task or needs my input
- Describe a feature or bug in plain language and have it automatically turned into a scoped implementation task
- Convert user feedback submissions into structured tasks with proposed scope
- Approve a task's scope and contract before an agent is allowed to modify the repository
- Assign a coding task to an agent directly from an existing issue or ticket
- Export all of my data in open formats and leave
- Self-host the core product
- Run many agent tasks concurrently to scale delivery throughput
- Run an agent headlessly inside CI/CD pipelines and shell scripts
GitHub README24 stories
- Run the product headlessly / in CI for automation
- Use an official CLI
- Set up automations that run autonomously in the background
- Delegate tasks to a built-in AI assistant inside the product
- Test against a sandbox environment without touching production data
- Perform bulk operations across many items at once
- Schedule recurring jobs or workflows
- Version, review, and roll back my automations
- Have an agent autonomously diagnose and fix a reported bug
- Have an agent implement a requested feature end-to-end, including writing tests
- Have an agent automatically clone the repo, install dependencies, and configure its own working environment
- Take over an in-progress agent task in my editor, terminal, or browser to finish or redirect the work
- Watch what a running agent is doing in real time, including its current status
- Get notified when an agent completes a task or needs my input
- Describe a feature or bug in plain language and have it automatically turned into a scoped implementation task
- Approve a task's scope and contract before an agent is allowed to modify the repository
- Assign a coding task to an agent directly from an existing issue or ticket
- Export all of my data in open formats and leave
- Read the product's source under an open license
- Self-host the core product
- Run a readiness report that evaluates how ready my repository is for autonomous agents
- Run many agent tasks concurrently to scale delivery throughput
- Self-host agent infrastructure locally, in containers, or on my own VMs
- Run an agent headlessly inside CI/CD pipelines and shell scripts
Package docs9 stories
- Run the product headlessly / in CI for automation
- Use an official CLI
- Drive the product through a documented public API
- Perform bulk operations across many items at once
- Have an agent automatically clone the repo, install dependencies, and configure its own working environment
- Convert user feedback submissions into structured tasks with proposed scope
- Self-host the core product
- Self-host agent infrastructure locally, in containers, or on my own VMs
- Run an agent headlessly inside CI/CD pipelines and shell scripts
Probe proofs — replayable recordings from the probe harnessProbe proofs
Replayable recordings from our probe harness — see the Prove-It protocol to submit one.
$npm view @yylo/cli name version binreproduced$ npm view @yylo/cli name version bin
name = '@yylo/cli'
version = '0.2.2'
bin = {
yy: 'dist/bin/yylo.sh',
ypl: 'dist/bin/ypl.sh',
yylo: 'dist/bin/yylo.sh',
'feedback-yylo': 'dist/bin/feedback-collector.mjs'
}
$curl -s https://raw.githubusercontent.com/yylo-dev/yylo/HEAD/LICENSE | head -3reproduced$ curl -s https://raw.githubusercontent.com/yylo-dev/yylo/HEAD/LICENSE | head -3 MIT License Copyright (c) 2026 JUNO AI INC.
Claims vs evidence — vendor claims reconciled against independent verdictsClaims vs evidence
3 of 10 testable claims verified · 3 contradicted → integrity 0/100
18 distinct capability claims found in YYLO’s own claimed-docs/GitHub materials, reconciled against our judge’s independent verdicts.
3
Verified
4
Unverified
3
Contradicted
21
Undersold
Verified (3)
“Official CLI (npm-installed) to initialize agent tasks, e.g. `yylo init --task ... --subagent claude`”
“A run emits a machine-readable watch receipt (state, exit code, log bytes) for CI verification”
Run an agent headlessly inside CI/CD pipelines and shell scriptspartialproof ↗
“`task start` freezes the target commit, creates a dedicated branch/worktree, and completes dependency hydration before marking the task working”
Have an agent automatically clone the repo, install dependencies, and configure its own working environmentpartialproof ↗
Unverified (4)
“Runs bounded concurrent fan-out across independent kanban tasks, data items, or commands, with structured evidence captured per item”
Run many agent tasks concurrently to scale delivery throughputpartialproof ↗
“Can resume a previously captured agent session by ID instead of reconstructing state from terminal scrollback”
Take over an in-progress agent task in my editor, terminal, or browser to finish or redirect the workpartialproof ↗
“Automatically repeats bounded iterations until no open kanban work remains”
Set up automations that run autonomously in the backgroundpartialproof ↗
“`doctor workspace` diagnoses topology problems with a nonzero exit code, without ever modifying the workspace”
Run a readiness report that evaluates how ready my repository is for autonomous agentspartialproof ↗
Contradicted (4)
“Starting a task creates an isolated worktree from an exact base commit; preflight is read-only, finish queues the committed candidate”
Have an agent safely execute code and install dependencies inside an isolated sandboxnoneproof ↗
“Imports Slack messages or GitHub issues into kanban and posts completed responses back to the originating thread”
Connect issue trackers like Jira, Linear, ClickUp, or Monday.com so agents can manage tickets directlynoneproof ↗
“Imports Slack messages or GitHub issues into kanban and posts completed responses back to the originating thread”
Tag an agent in a chat thread to discuss and delegate a bug or taskn/a
“Plans immutable experiments, runs isolated attempts, retains evaluator provenance, supports safe recovery, and produces bounded reports”
Have an agent safely execute code and install dependencies inside an isolated sandboxnoneproof ↗
Undersold (21)
Run the product headlessly / in CI for automationfullproof ↗
Drive the product through a documented public APIpartialproof ↗
Delegate tasks to a built-in AI assistant inside the productpartialproof ↗
Test against a sandbox environment without touching production datafullproof ↗
Perform bulk operations across many items at oncefullproof ↗
Define rules that trigger actions automatically on eventspartialproof ↗
Have an agent autonomously diagnose and fix a reported bugpartialproof ↗
Have an agent implement a requested feature end-to-end, including writing testspartialproof ↗
Switch away from automatic model selection to a specific model of my choicepartialproof ↗
Watch what a running agent is doing in real time, including its current statuspartialproof ↗
Get notified when an agent completes a task or needs my inputpartialproof ↗
Describe a feature or bug in plain language and have it automatically turned into a scoped implementation taskpartialproof ↗
Convert user feedback submissions into structured tasks with proposed scopepartialproof ↗
Approve a task's scope and contract before an agent is allowed to modify the repositorypartialproof ↗
Assign a coding task to an agent directly from an existing issue or ticketpartialproof ↗
Export all of my data in open formats and leavepartialproof ↗
Self-host agent infrastructure locally, in containers, or on my own VMspartialproof ↗
Claims outside our story set (8)
Real capability claims found in YYLO’s own materials, but no story in this arena’s taxonomy covers them yet — that’s feedback on the taxonomy, not a mark against the product.
“`yy loop` sequentially repeats arbitrary shell commands”
source ↗“Workflow contracts can be saved as reusable YAML files”
source ↗“Offers a direct open-standard install path that can install a whole repository or a single slug”
source ↗“Workflow Runner is used when a step consumes output (response, file, or session) from an earlier step”
source ↗“CLI ledger commands to create, sort/list, and fetch individual tasks”
source ↗“Release channel adds ID-first Records and typed profiles for task, wiki, workflow, and artifact data”
source ↗“Command-line orchestrator providing repeatable workflows and receipt-backed repository changes for coding agents”
source ↗“`merge land` composes an immutable task source into a private candidate with Git ref protection, requiring recomposition if the target moves”
source ↗
Business model
MIT-licensed open-source CLI distributed via npm (@yylo/cli); no paid hosted tier or public pricing page published today.
pricing ↗Score trend
How this product’s scores have moved as evidence and verdicts are re-derived — a point per change, not per day.
Try Experimental
Run it in the microterminal →Recorded agent sessions — and a live MCP handshake where the vendor ships one.
Flag
⚑ Flag a verdictThink a verdict is wrong? Opens a prefilled GitHub issue — or use the ⚑ next to any verdict above.
For agents