| What it does | Memory layer for AI coding agents that ties code, tickets, docs and conversations into one queryable graph
| 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 | Freemium
| Freemium
|
|---|
| Pricing | Local: free forever. Local + Server plans: Solo $15/month for one key, Team $99/month for 10 keys or $459/month for 50 keys, Enterprise custom. All paid plans include 18 connectors, better embeddings and reasoning, Oynix Ask and Oynix Wiki.
| 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 | - Connects 18 sources: GitHub, GitLab, Bitbucket, Slack, Microsoft Teams, Jira, Linear, Sentry, Confluence, Notion, Google Drive, Microsoft 365, Mixpanel, CleverTap, Firebase, Supabase, and custom file
- Builds live knowledge graph from code, tickets, docs and conversations
- MCP server integration with Claude, Cursor, Codex and 13+ agents
- Oynix Wiki: automatically generated engineering handbook with every claim traced to source
- Oynix Ask: query the graph and get exact nodes with source attribution
- Live presence: see who is editing in your codebase right now before your agent collides with their work
- No per-token, per-file, per-function or per-repository billing; pricing by seats only
| - 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 | - Runs entirely on your machine with no code uploaded to external servers, unlike vector search tools
- Returns exact graph nodes and paths instead of text chunks, with reasoning about who owns what and why it exists
- No per-token billing; your AI provider bills you for its own usage on your own key
- Memory stays and improves after each session, not lost between conversations like stateless agents
| - 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) | 26 | 14 |
|---|
| Referring domains (Majestic) | 22 | 4 |
|---|
Oynix
Backloop