Coding platform / PRODUCT DOSSIER

Kilo Code

An editor, CLI, and cloud agent with configurable models and roles.

IDE · CLI · cloud · Open source · MIT · cited repositoryRevision 2026-09-13.4 · unreviewedNeeds recheck · recheck 2026-10-130 attestations · checked 2026-09-13

What we do not know yet · 2 open gaps

  • Cloud Agent and code-review services are separate hosted surfaces.
  • CLI autonomous mode disables confirmations; it is not a sandbox.

Applies to: Repository documentation at c36e22634860e06e0aa63234fae37bbd83d3b182 · Documentation review only

Applicability, 3 recheck triggers & verification plan

Applicability

Repository documentation at c36e22634860e06e0aa63234fae37bbd83d3b182

Documentation review only

Excludes: Runtime behavior; Performance comparisons; Security guarantees

Recheck when

  • Documentation changes
  • New product release
  • License change

Needs recheck · due

Verification plan

  1. Pin a product release or repository commit and record the host environment.
  2. Create a disposable repository with a passing baseline test.
  3. Run a bounded change with two agents where supported; record permissions and logs.
  4. Record a failed attempt, actual outcome, and artifacts without secrets.
  5. Have another person reproduce the result before labeling it reproduced.

Provenance & review

Testedknowhow initial research

Commissioned by a Nimbalyst maintainer; not an independent comparison.

Revision 2026-09-13.4 · unreviewed · checked

0 attestations · Content: Unlicensed prototype; redistribution decision pending

Capability claims · 12 / 46 sourced

Standing condition: these are documentation claims at the source capture date, with outcome “claimed”; no runtime execution is recorded. Dossier applicability and limitations apply throughout. Expand a row for its statement, specific scope and contradictions. Numbered citations resolve to the source locator and capture date below. Missing evidence means Unknown, not No. Sources are unpinned unless marked “Pinned”; this marks source stability, not stronger support or runtime verification. Reuse counts refer to claims in the full dossier; repeated citations do not represent independent sources.

Yes Documented within scope Partial Limited form of the feature No Explicit evidence of absence Unknown No evidence recorded. These are support assessments, not quality scores or runtime verification.

Orchestration

Task managementYes
Explore Task management →

Plan agent prepares implementation plans.

Review & delivery

Change reviewYes
Explore Change review →

Includes a review agent for code changes.

Pull request workflowYes
Explore Pull request workflow →

Offers automated pull-request code reviews.

Work surface

Code editingYes
Explore Code editing →

Integrates with VS Code and JetBrains.

Terminal accessYes
Explore Terminal access →

Controls terminal commands.

Browser interactionYes
Explore Browser interaction →

Automates browser interactions.

Context & models

MCP toolsYes
Explore MCP tools →

Provides an MCP server marketplace.

Skills & custom agentsYes
Explore Skills & custom agents →

Supports custom specialized agents.

Model choiceYes
Explore Model choice →

Switches models during a task.

Execution & access

Remote executionYes
Explore Remote execution →

Offers a cloud agent accessible from the web.

Tool permissionsYes
Explore Tool permissions →

Documents an explicit flag that disables permission prompts.

Programmatic controlYes
Explore Programmatic control →

Supports headless CI execution through kilo run.

Unknown · 34 capabilities without evidence

Interface images & local attachments

Sources · 1

[1]Kilo Code · readme ↗Pinned12 / 12 claims
repository · locator & rights

c36e22634860e06e0aa63234fae37bbd83d3b182

README feature sections; license and limitations at this pinned revision.

Authored summary and link only; upstream rights retained.