Plugin Evaluation License

Choose this if you've outgrown Community on a plugin install

Community is enough to install a plugin, write a few policies, and watch governance fire. Evaluation is the right next step once you're running a plugin against real work and Community's 3-day audit window, 20 policies, and disabled approval queue start to bite.

Best for solo developers and small teams running a plugin in real IDE / CLI sessions, not just demos
Still self-hosted, still free, still safe to run inside your environment — your data never leaves your infrastructure
If you want direct rollout support, hook design review, and policy-pack scoping help, use the Plugin Design Partner Program

What plugin users actually gain

Audit window 3 → 14 days. Investigate "what did my agent do last week?" — not just "what did it do yesterday before logs rolled off?"
Tenant policies 20 → 50. Room for a real policy pack: secrets, prod-vs-dev, language-specific gates, MCP connector rules — not just a starter set
HITL approval gates ON. Plugin's high-risk actions actually pause for human approval. In Community mode, require_approval policies silently auto-approve
Evidence export ON. Compliance team can pull CSV/JSON of plugin-generated audit events (5,000 records / 14-day window / 3 exports per day)
Policy simulation ON. Test "will this rule break my agent?" before merging the policy — 300 simulations per day
5 connectors with custom policies (up from 2). Your plugin pairs with postgres + slack + filesystem? Now they all get governed

Most teams reach this page after running a plugin in Community for a sprint or two and hitting one of the limits above. Evaluation is sized to validate plugin-driven governance against real work, not to spread across the org.

Plugin tier comparison

Numbers below come directly from platform/agent/license/tier_support.go — the runtime config plugin requests evaluate against. Rows that don't apply to plugin users (MAP/WCP execution quotas, multi-agent plan caps, SSE streaming, cost-estimator limits) are omitted.

Capability	Community	Evaluation (Free)	Enterprise
Tenant policies	20	50	Unlimited
Org-wide policies	0	5	Unlimited
Connectors with custom policies	2	5	Unlimited
Audit retention	3 days	14 days	Up to 10 years
HITL approval gates	—	25 pending, 24h expiry	Unlimited, 24h expiry
Evidence export (CSV / JSON)	—	5,000 records · 14-day window · 3 / day	Unlimited
Policy simulation	—	300 / day	Unlimited
Session overrides (self-service unblock)	—	—	Enabled (24h cap, mandatory justification)
Decision explainability (`explainDecision`)	Available	Available	Available
Per-user identity (`X-User-Email`)	Available	Available	Available

Tenant policies — rules scoped to your organization (your team's deny rules for SQLi, secrets, dangerous shell commands, etc.)

Org-wide policies — cross-tenant rules an IT/CISO function applies to every developer using the plugin. Enterprise-only beyond the 5-policy Evaluation cap

HITL approval gates — high-risk plugin actions (e.g. tools tagged in highRiskTools) pause for human approval before executing. Disabled in Community mode (silent auto-approve)

Evidence export — compliance teams pull plugin-generated audit events as CSV/JSON for SOC 2 / ISO 27001 / regulator submission

Policy simulation — dry-run a policy before deploying it to see what it would have matched on real plugin traffic — keeps experimental rules from breaking working agents

Session overrides — a blocked developer can request a time-bounded, audit-logged exception with a free-text justification. Plugin Batch 1 surfaces override_available: true on every block; this is what lets the user actually act on it. Enterprise-only.

Decision explainability — every plugin block returns a decision_id; explainDecision() returns the matched policies, risk level, and override availability for incident review

Per-user identity — when the plugin sends X-User-Email, audit events and override grants are scoped to the actual human, not a synthetic shared client identity

When to request this

You're running a plugin against real IDE / CLI work and Community's 3-day audit window keeps rolling off events you wanted to investigate
Your starter policy pack hits the 20-policy ceiling and you have more rules to write
You want HITL approval prompts to actually fire when high-risk tools run, not silently auto-approve
Your compliance / security team has asked for audit evidence as CSV or JSON
You want to dry-run a new policy against real plugin traffic before merging it
You're considering Enterprise but want a free 90-day window to validate plugin-driven governance against the actual code your team writes first

Community is fully functional for installing the plugin and writing your first policies. Evaluation unlocks the capacity and the approval / export / simulation features that matter once governance is firing on real work. Free, 90 days, renewable. AxonFlow runs fully self-hosted, and anonymous telemetry can be disabled for regulated evaluations.

Typical plugin evaluation flow

Install the plugin (Claude Code, Cursor, Codex, or OpenClaw) and bring up AxonFlow locally
Verify governance fires on real coding sessions (you'll see decision_id, risk_level, and override_available on blocked actions)
Apply the Evaluation license, write your real policy pack, turn on HITL approval gates
Pull an audit export and confirm the events your compliance team needs are present

Most teams reach a real go / no-go decision within a few days of running the plugin against actual work.

What happens after you submit

Your evaluation license is sent directly to your inbox
You add it to your existing self-hosted deployment (no plugin reinstall required) and restart AxonFlow
You keep using the same plugin, IDE / CLI, and policies — capacity expands and approval / export / simulation features turn on
If you hit a blocker, you can reply directly to the email for help

If you'd rather get direct rollout help instead of going self-serve, request the Plugin Design Partner Program instead.

First name

Last name

Company or team (optional — leave blank if you're a solo developer)

AxonFlow ORG_ID

Check your docker-compose.yml ORG_ID value. Default is local-dev-org. This must match your deployed ORG_ID or old and new data will diverge.

Personal or work email is fine. We send your license key and setup instructions here.

Which plugin are you using?

What governance problem are you solving?

Where is this running?

Enable 5 business day priority support Free during evaluation. Get faster responses on setup issues and integration questions.

Free. No credit card. Valid for 90 days, renewable. No sales call. The license is sent directly to your inbox.

Check your email

Your license key and setup instructions have been sent to your email. Check your inbox (and spam folder).

Didn't receive it? Email [email protected] and we'll sort it out.

Want help getting started? Totally optional.

Book 15 min with the founder

Recommended next reads: plugin integration walkthrough, regulated-environment assessment, full tier comparison

What's the one thing that would make you not adopt AxonFlow?

Thanks, noted.

Want direct rollout help, hook design review, or a longer partnership motion? Apply for the Plugin Design Partner Program instead.

Questions? Email [email protected]