| What it does | Memory layer for AI coding agents that ties code, tickets, docs and conversations into one queryable graph
| An approval layer for unattended AI agents that halts risky actions for human approval before execution
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| Not given
|
|---|
| 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.
| Self-hosted: Free (MIT licensed). Hosted Indie: $49/mo (2 seats, monthly governed-action ceiling, 30-day retention, email support). Hosted Team: $199/mo (10 seats, higher governed-action ceiling, 90-day retention, org-scoped rate limits, priority support).
|
|---|
| 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
| - Intercepts risky agent actions before execution
- Works with Claude Code, Codex, Hermes, OpenClaw, and MCP
- Policy-based risk scoring and decision making
- Remote approvals from phone or browser
- Signed audit ledger with replayable records
- Calibrated interruptions that reduce false positives
- Enforcement liveness monitoring via synthetic probes
- Self-hosted (MIT licensed) or managed hosting options
- Approvals inbox with decision ledger and policies
- Agent defense documentation with assumptions and shields
|
|---|
| 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 approval layer that protects unattended runs that walk away
- Signed ledger with replayable audit records and explicit signature verification
- Self-hosted with no infrastructure lock-in or vendor dependency
- Learns from your approvals to reduce interruptions automatically
- Honest about enforcement boundaries across different integrations
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | Not checked yet ● no change since last check | 8 ▲ +1 (up) since last check |
|---|
| Trust Flow (Majestic) | 0 | 3 |
|---|
| Citation Flow (Majestic) | 26 | 30 |
|---|
| Referring domains (Majestic) | 22 | 88 |
|---|
Oynix
DashClaw