| What it does | The execution replay engine for AI agents
| Memory layer for AI coding agents that ties code, tickets, docs and conversations into one queryable graph
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | IN
| Not given
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | Free plan includes 1,000 traces/mo and 7-day retention. Starter at $29/mo adds 10,000 traces/mo and 30-day retention. Pro at $99/mo includes 50,000 traces/mo, 90-day retention, and unlimited fork replays. Teams at $399/mo provides 500,000 traces/mo, 365-day retention, up to 10 users, and 1,000 prove
| 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.
|
|---|
| Key features | - Record every LLM call, tool call, and error with one decorator
- Step-by-step replay of agent executions
- Fork and cascade-replay from any failing step
- Prove-the-fix verification before shipping
- Runtime guardrails and circuit breakers
- CI/CD regression gates
- Multi-agent session tracking and topology graphs
- Automatic hallucination and drift detection
- Semantic search across agent runs
- PII auto-redaction on every plan
| - 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
|
|---|
| What makes it different | - Turns production failures into regression tests that fail builds when behavior breaks
| - 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
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 6 ▲ +1 (up) since last check | Not checked yet ● no change since last check |
|---|
| Trust Flow (Majestic) | 20 | 0 |
|---|
| Citation Flow (Majestic) | 25 | 26 |
|---|
| Referring domains (Majestic) | 115 | 22 |
|---|
Retrace
Oynix