| What it does | AI agents say done. rightcommit proves it.
| Catch where AI agents get stuck on your API or MCP server, rank problems by impact, and draft fixes as pull requests
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| US
|
|---|
| Pricing model | Open source
| Freemium
|
|---|
| Pricing | Free to self-host under FSL-1.1-ALv2. No license fee; pay only for AI model usage with your own accounts.
| Open source: free. Team: $199/month with 14-day free trial (1 API or MCP service, 25,000 reports/month, 15 coding-agent runs/month). Business: $799/month (up to 3 services, 250,000 reports/month, 60 coding-agent runs/month). Extra coding-agent runs: $6 each.
|
|---|
| Key features | - Visual workflow canvas with drag-and-drop design
- Project Manager assistant that converts goals into workflows
- Automatic tests and independent agent reviews before approval
- Version control with SHA-256 fingerprints and line-by-line diffs
- Cost breakdown by step, agent, model and run
- Integrations with GitHub, Azure DevOps, ServiceNow, Jira and Confluence
- MCP and A2A support for custom tools and agent-to-agent workflows
- Configurable autonomy from interactive to fully unattended
- Encrypted credential storage with keys never sent to browser
| - Session replay for MCP servers to identify failed agent sessions
- Clustering reports by agent goals and workflows
- Priority ranking weighted by frequency, failed workflows, and affected accounts
- Claude Code generates pull requests with tests
- Review queue with diff, tests, agent reports, and evidence
- Isolated git worktree prevents unauthorized code push
- Schema validation and rate limiting for feedback
- Open Agent Feedback Protocol with TypeScript and Python SDKs
- GitHub integration for draft PR creation
|
|---|
| What makes it different | - Code and credentials stay on your servers, never sent to AI agents
- Independent reviews by second agent before any approval
- No automatic code pushes or deployments without your confirmation
- Transparent per-step cost tracking with input/output tokens and reasoning costs
- Fair Source license allows professional services for clients
| - Only AI agent failures on successful HTTP responses get detected and ranked
- Automated pull request drafts with your approval required before shipping
- Session replay captures failures even when agents don't report them
- Pay only for coding-agent runs, not feedback submission
- Open protocol and SDKs can be self-hosted at no cost
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | Not checked yet ● no change since last check | 1 ● no change since last check |
|---|
| Trust Flow (Majestic) | 0 | 1 |
|---|
| Citation Flow (Majestic) | 0 | 14 |
|---|
| Referring domains (Majestic) | 0 | 4 |
|---|
rightcommit
Backloop