
agent-orchestrator
AgentRun many coding agents in parallel, each on its own branch, with PR and CI feedback loops
- Open source
- Open-source agent
- 14.9K GitHub stars
- Coding

Run many coding agents in parallel, each on its own branch, with PR and CI feedback loops
Offline review that flags agent changes which weaken tests, assertions or CI
Runs locallyRun WCAG 2.2 accessibility audits and vision simulations on any URL from an agent
Runs locallyDated upstream changes that will break code, checked against your repo or dependencies
Runs locallyA lockfile for MCP tools: blocks changed tool definitions and signs a receipt per call
Runs locally
Rank security scanner findings by exposure, criticality and exploitability
Runs locallyFind and free developer cache and old node_modules disk space, with an AI-assistant mode
Runs locallyPlanning and report-checking MCP server for change-aware CI validation by coding agents
Open-source MCP server scoring pull-request risk from blast radius and git history
Runs locallyAPI tests in YAML that coding agents write and a 9 MB native binary runs in CI
Runs locallyOffline trust certificates for code repositories that anyone can re-run and verify
Runs locally
Finds why Playwright tests fail, proposes fixes and verifies them before keeping the edit
Runs locallyCheck a text file of links for status codes, broken pages and redirect chains
Runs locally
Test BGP and routing changes in a real containerlab lab before merge, with evidence
Runs locallyRust-based Odoo addon linter with OCA rule parity, exposed to AI agents over MCP
Runs locallyCI runner cost, flaky tests, failures and coverage from BuildPulse inside your AI agent
Not checked yetRead-only check that your machine meets a project's declared Node, Python and Git versions
Runs locallyRead-only preflight checks for MCP and x402 endpoints before an agent depends on them
Runs locallyCapture a live site and measure it against your Figma library, tokens and source code
Runs locallyFind and remove AI-writing patterns from text with fixed rules, offline
Runs locallyPins MCP tool definitions at approval and blocks the session when they change
Runs locallyRun eight-view mobile checks on AI-generated web pages and get repair-ready evidence
Runs locallyGives coding agents your repo's engineering standards and checks their changes
Runs locallyRead-only MCP server that lets coding agents query Playwright test stability and failures
Runs locallyInspect a remote MCP server's transport, tools and side-effect hints without calling tools
Not checked yet
MCP server that lets coding agents record, slow down and test app animations
Runs locallyRun rooted Android emulators on Apple Silicon Macs, driven by a CLI or AI agents
Runs locallyLocal Google Cloud emulation for coding agents, with 25 services in one Docker container
Runs locallyCheck pages for responsive design problems and screenshot them on real device sizes
Runs locallyOffline secret scanning MCP server that returns redacted findings to coding agents
Runs locally