Features
Build features, repair errors, and improve code quality in one workspace. Define the work, follow execution, and inspect changes with independent validation evidence. You decide what merges.
Infinite Coder
From a requested feature to changes you can review
Describe what you want built or start from a connected issue. Infinite Coder proposes a plan for your approval, implements the change, and runs required validation. Repair attempts happen within the run, followed by a final review of the whole program. See how it works.
Capabilities
- Plan approval: review the proposed scope, risks, assumptions, and validation targets before execution.
- Greenfield-ready: seed a starter (FastAPI, Flask, Express, React, Vue, Svelte, or Astro) or start from an empty repo.
- Configurable limits for time, iterations, and tokens, with automatic detection of when work is done.
- Every run is inspectable and resumable, its attempt ledger showing validation, repair, and review events inline.
- Automated test validation across 10 stacks: Python, JS/TS, Go, Rust, Ruby, PHP, .NET, JVM via Maven/Gradle, C/C++ via CMake/CTest.
Runtime Error Tracking & HotFix
From runtime error to a validated, reviewable fix, automatically
Sentry-powered monitoring connects runtime errors to proposed fixes and their required validation. Frequent errors become repair candidates through an opt-in trigger with cooldown windows and daily budgets. Fixes land on isolated local delivery branches; push is disabled by default. Read about HotFix.
Capabilities
- Repair retries resume the prior attempt's memory instead of cold-restarting.
- A STAGED status marks a fix verified on a branch but not yet published.
- A successful fix automatically resolves the linked Sentry issue.
- Full logs and diffs attached for every fix, plus repair scheduling from preview failures.
- Failed attempts stay isolated from the target branch, with run status and diagnostics available for inspection.
Source Control & Preview
Review AI-generated changes and watch them run, without switching tools
Source Control shows commit history, branch context, and per-file diff review in one surface. Container Preview runs your app alongside that history, feeding runtime signals straight into HotFix triage. A preview quality gate measures Core Web Vitals, accessibility, and bundle size, and every preview container gets a signed identity with egress blocking. See source control & integrations.
Capabilities
- Project-scoped git graph and commit timeline with inline diff review.
- Compare view: diff any earlier commit against the selected revision.
- Start, restart, and stop preview containers with live runtime verification.
- Preview quality gate: Core Web Vitals, accessibility, bundle size, and console errors on the exact revision.
- Signed, network-isolated container identity with active egress blocking to protected infrastructure.
Agentic Runtime
Reliable multi-step execution with budgets, checkpoints, and automatic completion detection
CrewWork tracks execution, budgets, and Git checkpoints so interrupted work can recover from saved state. Pause or resume supported runs, inspect their history, and see why work stopped. Completion requires evidence from the platform’s validation process. See the architecture.
Capabilities
- Persistent run state with project-level progress logs across restarts.
- Configurable limits for iterations, tokens, and wall time.
- Start work from CrewMate chat, the Run Composer, or project surfaces.
- Git checkpoints and saved run state support recovery and review.
- Full task summaries and logs for every run.
Continuous Improvement
Turn coverage gaps and code findings into scoped work
CrewWork identifies coverage gaps and code improvement opportunities, then proposes scoped work with supporting evidence. Suggestions are reviewed for impact, risk, and confidence before reaching your queue. Start a coverage improvement run from a measured file and revision in Quality & Security.
Capabilities
- Generates single-PR-sized recommendation tasks with impacted files and validation footprint.
- Evidence required: each suggestion cites real file paths and code excerpts.
- An Improve action starts a reviewed run scoped to a low-coverage file at its measured baseline.
- Tracks applied vs. dismissed outcomes for feedback loops.
- Produces risk and context summaries with each recommendation.
Reliability and Governance
Automation that survives restarts, respects budgets, and keeps every decision auditable
CrewWork persists every task, budget, and checkpoint to Postgres, so runs survive restarts, with workspace locks preventing conflicting automation. Validated builds can deploy to hosts on your own network through a mutual-TLS release agent, with on-call escalation if a deployment fails. See releases & on-call.
Capabilities
- Resumable, checkpoint-based recovery for runs and queues.
- Configurable budget governors for tokens, time, and iterations.
- LAN release agent: outbound-only, mutual TLS, no inbound connectivity to the target.
- Compliance evidence reports: non-certifying, project-scoped views across eight evidence areas.
The Workbench
A full development workbench anywhere you have a browser. Agents write the code; you review it
CrewWork's workbench brings Source Control, Preview, a file Explorer, and a read-only Monaco code reader (same engine as VS Code) into your browser, alongside Work, Projects, Organization, and the admin-gated CrewWork Control console. The CrewMate assistant panel answers questions grounded in your repository and speaks MCP directly to external tools. See platform & safety.
Capabilities
- File explorer with directory navigation and multi-tab file review.
- Command palette with quick open, symbol search, and repository clone.
- Spec-compliant MCP server: external clients read files, search code, and inspect git status, read-only.
- Charter-driven programs and a suggestion pipeline generate persistent task queues.
- Runs view with logs, checkpoints, and real-time updates across runs and scans.
Work, Runs, and Evidence
See what happened, when, and why, across project and platform runs
The Inbox separates Needs you, Active, and Done so you can find decisions and follow progress. Open a run to inspect its timeline, changes, validation evidence, and logs. Action Items and Campaigns organize follow-up work; Background Jobs tracks the platform task queue. See how it works.
Capabilities
- Timeline view for run and step progression.
- Status and transition visibility across workflows.
- Cross-run context for debugging and review.
- Project-linked activity filtering.
Code Intelligence
Search and navigate your codebase by meaning
Search your codebase by intent, for example "where do we handle user authentication," and get relevant results. Structural analysis builds a symbol graph with complexity metrics so you can jump to definitions, find references, and trace relationships, with optional AI explanations for undocumented symbols. See the architecture.
Capabilities
- Go-to-definition and find-all-references across your entire codebase.
- Multi-language support: Python, JavaScript, TypeScript/TSX, Go, Rust, Java, C/C++.
- Duplicate-code detection surfaced in your project Health Score.
- Reviewed refactoring recipes with a hash-verified preview before any change applies.
- Cross-project semantic search and batch refactoring across projects you can access.
Security Scans
Know your vulnerabilities before attackers do
CrewWork runs project security scans across 18 scanner profiles: SAST for Python, JS/TS, Go, Ruby, C/C++, and Java, dependency and license checks, secret scanning, infrastructure-as-code analysis, and opt-in DAST (passive baseline, plus bounded active web and API modes) against your running preview. See security.
Capabilities
- Dependency and license-policy checks with reachability evidence.
- Secret scanning and infrastructure-as-code analysis.
- SARIF, SBOM (SPDX), and OpenVEX export, plus SARIF import as the canonical latest scan.
- On-demand vulnerability fix actions per finding.
- Scan status and results in the Projects security panel.
Provider Integrations
Fits into the git workflow your team already uses
CrewWork connects to GitHub, GitLab.com, Bitbucket Cloud, and Jira Cloud, one connection per provider per organization. GitHub gets the deepest automation: automatic PR review comments and a five-part quality gate posted as its own status check before anything merges. Platform self-repair opens draft PRs; project fixes push only when enabled.
Capabilities
- OAuth or API-token connections for GitHub, GitLab.com, Bitbucket Cloud, and Jira Cloud.
- Automatic PR review comments with ownership, CODEOWNERS gaps, and blast-radius impact analysis.
- Five-part quality gate posted as its own GitHub status check.
See how it all fits together
Explore the system architecture or review the platform operating model.