Skip to content

The datasheet for every AI agent

Research report · data-report

In your pipeline: a census of 110 listings

29 of 110 listings answer yes for “In your pipeline”. Counted from our own datasheet, with the query that reproduces every figure.

Sep 8, 20262 min readSource-linked research

In your pipeline, across 110 settled listings

  1. Yes29 of 110

  2. Qualified26 of 110

  3. No16 of 110

  4. Does not apply33 of 110

  5. Not established6 of 110

Of the 110 Published listings whose datasheet settles “In your pipeline”, the largest group is “Does not apply” at 33 (30%). Measured 2026-09-08.

Denominator: 110 Published listings whose datasheet settles “In your pipeline”.Method: Counted from the stored datasheet answer for “In your pipeline” across every Published listing, all of which have a recognised stored answer on that row.Measured .
Cite this chart

Reuse this chart anywhere, with credit. Paste this HTML — it links back to the report the numbers come from.

<a href="https://theagentsindex.com/blog/surface-ci-census/" target="_blank" rel="nofollow noopener"><img src="https://theagentsindex.com/charts/surface-ci-census.png" alt="In your pipeline, across 110 settled listings — The Agents Index" title="In your pipeline, across 110 settled listings — The Agents Index" width="640" loading="lazy" style="max-width:100%;height:auto" /></a>

Explore the matching agents

In your pipeline · Datasheet criterion surface_ci · Report counted .

Current listings as of ; this set may differ from the report's original sample. Includes “Yes” and “Qualified” answers only. Read the conditions on qualified answers before treating them as a match. “No”, “Not applicable” and “Not established” answers are excluded.

View 55 current matching records
  • Ada Qualified

    The Platform API can be driven from a CI pipeline to push tools and MCP clients run in non-interactive environments, but there is no pull-request or build-check surface.

    Source retrieved 2026-09-09

  • Agent Development Kit (ADK) Yes

    Evaluation and conformance runs are exit-code CLI tools meant to gate a pull request; the agent runs inside CI rather than commenting on the diff.

    Source retrieved 2026-09-02

  • AgentsKit.js Yes

    Eval results render as JUnit, Markdown or GitHub annotations that can fail a pull request, and a GitHub Actions snippet shows the wiring.

    Source retrieved 2026-09-09

  • Augment Code Yes

    --print mode is built for CI/CD, and GitHub/GitLab triggers act on pull requests and failed runs.

    Source retrieved 2026-09-02

  • Botpress Qualified

    A bot can subscribe to pull-request and issue events and post comments through the GitHub integration, but there is no GitHub Action or CI runner: shipping is the local adk deploy command.

    Source retrieved 2026-09-02

  • Browserbase Yes

    Documented GitHub Actions workflow creates a session, inspects the live DOM and opens a pull request.

    Source retrieved 2026-09-02

  • Cartesia Qualified

    Deployments can be triggered by pushing to a linked GitHub repository, but there is no pull-request or CI review surface.

    Source retrieved 2026-09-02

  • Claude Agent SDK Yes

    Bare mode exists for CI reproducibility, and exit codes plus init-event fields let a pipeline fail on a bad run.

    Source retrieved 2026-09-02

  • Claude Code Yes

    GitHub Actions and GitLab CI/CD run it in your own pipelines; a managed GitHub PR reviewer exists on Team and Enterprise.

    Source retrieved 2026-09-02

  • Cline Yes

    Headless CLI runs in GitHub Actions and any pipeline; docs supply a PR-review workflow.

    Source retrieved 2026-09-02

  • CodeRabbit Yes

    Reviews post on pull requests across GitHub, GitLab, Bitbucket and Azure DevOps, and the CLI runs inside your own pipeline.

    Source retrieved 2026-09-02

  • Codex CLI Yes

    codex exec runs non-interactively in pipelines, with JSONL output and API-key or workload-identity auth.

    Source retrieved 2026-09-02

  • CrewAI Qualified

    Agents create and update GitHub issues and cut releases through the AMP integration, which the same page says needs an active subscription; no pull-request review or CI-runner action is listed.

  • Cursor Yes

    The CLI runs headless in CI with an API key, and Bugbot acts on pull requests as a pre-merge check.

    Source retrieved 2026-09-02

  • Decagon Yes

    Agent versions can be tested inside existing CI/CD practices before release.

  • Devin Yes

    Creates pull requests and answers PR comments inside your repositories once the SCM integration is installed.

    Source retrieved 2026-09-02

  • Devin Desktop Qualified

    PR review automation over a GitHub org is an Admin Portal toggle and agent PRs surface in Spaces, but the IDE does not run as a CI job; Devin Review is a separate product line.

    Source retrieved 2026-09-03

  • Dify Qualified

    The CLI is documented for CI pipelines, so apps can run as a build step; there is no pull-request review or repo-acting surface.

    Source retrieved 2026-09-02

  • ElevenLabs Agents Yes

    Agents deploy from CI with an API key in the environment; the unit of change is the agent configuration, not a pull request in your code.

    Source retrieved 2026-09-02

  • Factory Yes

    Droid Exec plus the Factory-AI/droid-action GitHub Action review and act on pull requests inside your runners.

    Source retrieved 2026-09-02

  • Gemini Code Assist Yes

    Acts on pull requests through the Gemini Code Assist on GitHub app, quoted at 100+ PR reviews per day; its enterprise version is in Preview. No other CI runner integration is documented.

    Source retrieved 2026-09-02

  • Genspark Qualified

    Claw connects GitHub under Developer Tools and can act on pull requests via a saved session; no CI runner, webhook or PR-triggered automation is documented.

    Source retrieved 2026-09-02

  • GitHub Copilot Yes

    Copilot CLI runs in GitHub Actions with the built-in GITHUB_TOKEN, and both code review and the cloud agent execute on Actions runners and consume Actions minutes.

    Source retrieved 2026-09-02

  • Glean Qualified

    Agents act on pull requests through the GitHub API, writing comments, descriptions and patches, but Glean runs no CI job of its own and respects existing branch protections.

    Source retrieved 2026-09-02

  • Google Antigravity CLI Yes

    Headless mode is documented for CI with JSON and NDJSON output and exit codes; no pull-request bot or hosted CI app is documented.

    Source retrieved 2026-09-02

  • goose Yes

    Documented as a GitHub Actions job that comments on pull requests; the guide's worked example is automated PR code review.

    Source retrieved 2026-09-02

  • HOL Guard Qualified

    Runtime Guard is a local daemon and does not act on pull requests; CI gating comes from the separate plugin-scanner and its published GitHub Action, which fails a PR on severity or trust score.

    Source retrieved 2026-09-07

  • Juggler Qualified

    `juggler run` is built for CI jobs, git hooks and batch work with typed exit codes, but there is no PR-review or CI integration of its own.

    Source retrieved 2026-09-02

  • Junie Yes

    Official GitHub Action triggered from issues and PR comments, a GitLab CI/CD integration, and a generic headless mode.

    Source retrieved 2026-09-02

  • Kilo Code Yes

    Reviews can fire automatically on PR creation, and Cloud Agent sessions can be started by webhook.

    Source retrieved 2026-09-02

  • LangChain Yes

    dcode runs headless with turn and time budgets and exit code 124 for CI; Engine opens pull requests on a connected GitHub repo.

    Source retrieved 2026-09-02

  • Langflow Qualified

    The DevOps toolkit scaffolds GitHub Actions to validate, test and push flows, but nothing claims Langflow itself reviews or acts on a pull request.

    Source retrieved 2026-09-03

  • LangGraph Yes

    The vendor publishes a CI/CD reference pipeline with a companion repository: tests and offline evals on a PR, then quality-gated preview and production deploys via the Control Plane API.

    Source retrieved 2026-09-02

  • Letta Yes

    A GitHub Action triggers agents from issues and PR comments, or automatically on pull_request events.

    Source retrieved 2026-09-02

  • LiveKit Agents Qualified

    CI is a deployment surface, not an acting surface: an official GitHub Action deploys the agent on push. The agent itself never acts on a pull request.

    Source retrieved 2026-09-02

  • LlamaIndex Qualified

    CI use is deployment only: a spec kept in source control, applied on every push.

  • Mastra Qualified

    Scorers and eval suites run in CI through Vitest/Jest via runEvals; the vendor claims no agent that acts on a pull request.

    Source retrieved 2026-09-02

  • MindStudio Qualified

    The Node client is documented for CI/CD use, with an offline type-sync mode and API keys held as CI environment variables, but no pull-request, commit or repository integration is published.

    Source retrieved 2026-09-02

  • Moveworks Qualified

    An ambient agent can be triggered by GitHub webhooks including pull_request events and act through HTTP Actions, but there is no CI integration or PR review surface of its own.

    Source retrieved 2026-09-02

  • Muse Code Yes

    muse exec runs one prompt to completion in a pipeline with META_API_KEY from a secret store; the sandbox needs working bubblewrap on a Linux runner, and no pull-request bot integration is documented.

    Source retrieved 2026-09-02

  • n8n Yes

    Git source control with workflow diffs gates what reaches production, the n8n CLI page names CI/CD pipeline integration as a fit, and the GitHub Trigger node fires on pull request events.

    Source retrieved 2026-09-02

  • OpenClaw Qualified

    A CI job can start and observe agent runs over the Gateway WebSocket RPC protocol, and the publication broker opens pull requests; there is no first-party GitHub Action or PR-triggered reviewer.

    Source retrieved 2026-09-02

  • OpenCode Yes

    It executes inside your GitHub Actions runner, and a parallel integration runs it in GitLab CI or GitLab Duo.

    Source retrieved 2026-09-02

  • OpenHands Yes

    Ships GitHub Actions plugins for PR review and QA that fire on pull-request events, plus a headless CLI mode with JSONL output for pipelines.

    Source retrieved 2026-09-02

  • Perplexity Qualified

    The Agent API can open and update pull requests through the GitHub connector, which is in preview; no CI runner or GitHub Action is documented.

    Source retrieved 2026-09-02

  • PolyAI Yes

    poly push is CI-compatible and the Agents API lets a pipeline gate promotion on a passing simulation-test set.

    Source retrieved 2026-09-02

  • Salesforce Agentforce Qualified

    Agent tests run in a CI system via Salesforce CLI and DevOps Center tools handle pull requests and pipeline promotion, but Salesforce documents no agent that runs on a pull request by itself.

    Source retrieved 2026-09-03

  • Sierra Qualified

    An agent release can be pushed from your CI/CD pipeline, but the agent does not act on pull requests or run build jobs.

    Source retrieved 2026-09-03

  • Sim Qualified

    Deploy, undeploy and rollback are API calls intended for CI/CD pipelines; there is no pull-request review surface.

    Source retrieved 2026-09-03

  • TinyFish Qualified

    The CLI documents a headless CI/CD authentication path, but nothing acts on a pull request or reports into a build.

  • UiPath Agent Builder Qualified

    UiPath publishes a complete GitHub Actions recipe that packs and deploys agent solutions, but the pricing comparison puts pipeline integration in the Enterprise column only, with an em dash against both Basic and Standard.

    Source retrieved 2026-09-03

  • Vapi Qualified

    Evals run as pipeline quality gates via API and CLI; there is no pull-request surface because there is no code to review.

    Source retrieved 2026-09-03

  • Vecbase Qualified

    An agent can act on GitHub through a scoped OAuth grant, including opening pull requests; no CI runner or pipeline integration is published.

    Source retrieved 2026-09-03

  • Warp Yes

    Two paths onto a pull request: the oz-agent-action GitHub Action inside your workflows, or mentioning the GitHub App on an issue, PR or review comment with no workflow file.

    Source retrieved 2026-09-03

  • zot Qualified

    JSON mode is pitched at CI and emits NDJSON events, but no pull-request, GitHub Action or forge integration is documented; you wire the binary in yourself.

    Source retrieved 2026-09-03

The population

110 listings in this index are Published. This is the population as of 2026-09-08. 110 of the 110 published listings in this index carry a settled answer for “In your pipeline”. That row asks: Can it act on a pull request or in CI? Every listing in the index is settled on this row, so nothing is left out.

Findings

  1. 29 of the 110 settled listings answer “Yes” for “In your pipeline”. That is 26% of the settled set.

  2. 26 of the 110 settled listings answer “Qualified” for “In your pipeline”. That is 24% of the settled set.

  3. 16 of the 110 settled listings answer “No” for “In your pipeline”. That is 15% of the settled set.

  4. 33 of the 110 settled listings answer “Does not apply” for “In your pipeline”. That is 30% of the settled set.

  5. 6 of the 110 settled listings answer “Not established” for “In your pipeline”. That is 5% of the settled set.

1 of those yes answers is Agent Development Kit (ADK), which still answers yes for “In your pipeline”. Its listing carries the stored answer and links to the source recorded for it. This is one worked example, not an independent audit of every source in the census.

What we counted, and how

Each figure above is a count over the “In your pipeline” row of the listing datasheet, taken from the same stored answer the listing page renders. The denominator is the 110 listings whose answer is settled, meaning one of yes, qualified, no, does not apply, not established. On this row that is the whole index, because every listing has a recognised stored answer. Every number here is stored with the read-only query that reproduces it and re-run every sixty seconds against the live corpus, so a figure that stops reproducing surfaces as drift rather than as a stale sentence nobody notices. Our full method covers how a datasheet row is settled in the first place.

Limitations

This counts stored datasheet answers, not independently tested capabilities. A sourced answer can record a vendor statement or our reading of published evidence; this census does not re-fetch those sources. “Not established” means we have not established an answer. That can reflect vendor nondisclosure, blocked evidence, or unfinished research, not a no. An absent or unrecognised answer is excluded rather than treated as a researched finding. The figures are restated when the stored corpus changes; the date above is the count used for this published version, not a new verification of the vendors.

Get the next report

New agents rankings and fresh data reports. One short email, one-click unsubscribe.