Skip to content

Features

Everything Novyx ships — memory, rollback, audit, and the tools built on top.

Memory Store & Recall

Store observations with tags, importance scores, and context. Recall semantically — ask a question, get ranked results in milliseconds.

  • Sub-100ms semantic recall
  • Importance scoring and tag filtering
  • Survives restarts, crashes, redeployments
  • Share across agents with Context Spaces
View API reference →
Memory Store
Stored Memories4 items

User prefers async communication

8
preferences
2m ago

Project deadline is March 15

9
project
5m ago

Dark mode enabled across all apps

5
uipreferences
12m ago

Weekly standup moved to Tuesdays

6
workflow
1h ago
Semantic Search
how does the user communicate?

User prefers async communication

0.94
preferences

Weekly standup moved to Tuesdays

0.71
workflow

Dark mode enabled across all apps

0.58
uipreferences

Magic Rollback

Point-in-time restore for your agent's memory. Preview what will change before executing. Like git reset for agent state.

  • Restore to any point in time
  • Preview changes before executing
  • Compensation plans for side effects
  • AI-suggested rollback points
View API reference →
Magic Rollback
10:01Store
10:03Store
10:05Update
10:08Store
10:12Delete
10:15Store
10:18Update
Rollback here
Created
Updated
Deleted
Rollback point
Removed
3memories after rollback point
Restored
2memories to previous state

Knowledge Graph

All plans

Your agent doesn't just remember facts — it understands relationships. Store structured triples, traverse entities, and build smarter agents.

  • Subject–predicate–object triples
  • Entity traversal and auto-dedup
  • Cascade deletes for clean removal
  • Force-directed graph visualization
View API reference →
Knowledge Graph
informsrelates_torequiresinvolvessetstracksconstrainsUser prefsProject goalsMeeting notesArchitectureDeadlinesTeam context

Cryptographic Audit Trail

Every memory operation is SHA-256 hashed and timestamped. Tamper-proof, exportable, and independently verifiable.

  • SHA-256 cryptographic hashing
  • Hash-chained operations
  • CSV/JSON export for compliance
  • RSA-signed execution traces
View API reference →
Audit Trail
SHA-256 verified
TimestampOperationAgentHashStatus
10:18:42CREATEagent_alphaa3f8c2...e91b
10:18:45UPDATEagent_alpha7d2e1f...b4a3
10:19:01CREATEagent_betae5c9a7...2f18
10:22:30ROLLBACKagent_alpha91b3d4...c7e2
10:22:31DELETEsystemf4a2b8...3d91

Execution Traces

All plans

Record every step of your agent's reasoning chain. Thought, action, observation, output — cryptographically signed and hash-chained.

  • THOUGHT → ACTION → OBSERVATION → OUTPUT
  • RSA-4096 signed, hash-chained
  • Independently verifiable
  • Integrates with Replay time-travel
View API reference →
Execution Trace
💭THOUGHT

User asked about Q4 priorities — checking memory...

ACTION

nx.recall("Q4 priorities", limit=5)

👁OBSERVATION

3 memories found: budget review, team expansion, launch date

💬OUTPUT

Based on your notes, the Q4 priorities are...

RSA-4096 signed|Hash-chained|Independently verifiable

Compensation Webhooks

New

All plans

When a rollback detects side effects in your traces — API calls, webhook fires, external writes — Novyx generates a compensation plan and notifies you.

  • Automatic side-effect detection
  • Reversal plan in execution order
  • Slack and Discord native formatting
  • Acknowledge actions as completed/failed/skipped
View API reference →
Compensation WebhooksNew
↩️
Rollback

triggers scan

🔍
Scan traces

find side effects

📋
Plan created

reversal actions

🔔
Webhook fires

Slack / Discord

N
Novyxvia webhook

Rollback compensation: 3 actions need attention

Reverse API call to /v1/external/notify
Undo webhook fire to Slack #alerts
Revert external DB write (users.preferences)

Eval — Memory Health Scoring

New in v3.0.0

Score your agent's memory health, detect regressions before they reach users, and gate CI/CD deployments on memory quality. The only SDK that tells you if your agent is getting dumber.

  • Composite health score (0-100) from recall, drift, conflicts, staleness
  • CI/CD quality gate — block deploys below your threshold
  • Baseline regression testing — save queries, detect when results degrade
  • Drift analysis — track topic churn, importance shifts over time
  • Eval history with per-tier retention up to 365 days
View eval docs →
nx.eval_run(min_score=80)
91.2

Health Score

500 memories · 0 conflicts · 140 stale

PASSEDmin: 80.0
Recall Consistency95
Drift Score88
Conflict Score100
Staleness Score72

$ curl -X POST /v1/eval/gate -d '{"min_score": 80}' --fail-with-body

exit 0 — deploy proceeds

Runtime v2 — Agent Lifecycle

New in v2.4.0

All plans

First-class primitives for orchestrating autonomous agents. Create agents that persist across sessions, assign goal-oriented missions, save checkpoints, and intervene when it matters.

  • Agents — create, inspect, delete. Persistent identity across sessions
  • Missions — goal-oriented task orchestration with pause, resume, cancel
  • Capability Packs — define which tools an agent can use. Policy at the orchestration layer
  • Checkpoints — save and restore agent state. Rollback to any checkpoint
  • Supervisor Interventions — inspect and override agent decisions in real-time
View Runtime v2 docs →
Runtime v2 — Agent Lifecyclev2.4.0
research-agentagt_f7a2
4h 12m
Audit Q1 vendor contracts
chk_03
running
deploy-agentagt_c3b8
1h 38m
Roll out v2.4 to staging
chk_07
paused
Intervention Required12s ago

deploy-agent wants to run: kubectl apply -f prod/rollout.yaml

More Core capabilities

Cortex

New

Autonomous memory intelligence. Auto-merge duplicates, boost important memories, decay noise, and surface patterns.

Explore Cortex →

Webhooks

All plans

Real-time event notifications. HMAC-signed payloads with Slack and Discord native formatting.

View docs →

Teams

All plans

Invite your team to a shared memory namespace. Owner, admin, member, and read-only roles.

View docs →

Context Spaces

All plans · sharing on Pro+

Agent A learns it, Agent B knows it. Shared memory across your entire agent fleet.

View docs →

Milestones

All plans

Tag meaningful points in your timeline — deployments, model swaps, prompt changes. Diff before vs. after.

View docs →

Hygiene

New

Context hygiene for agentic coding. Auto-persists Claude Code sessions across /compact, /clear, and restarts via hooks. Health scoring included.

View docs →

Agent SDK

New

Build agents with built-in memory. Auto-recall before every response, auto-remember after. Works with OpenAI, Anthropic, or any LiteLLM model.

View docs →

Control

New

Action governance for AI agents. Policy engine, approval flows, and cryptographic audit trail for every tool call that touches the real world.

View docs →

Sentinel Circuit Breaker

Automatic protection against cascading failures. Configurable fail-open/fail-closed modes. Free on every plan.

View docs →

Replay — Time-Travel Debugging

All plans

See exactly what your agent knew when it made a decision. Timeline, snapshots, diffs, counterfactual recall, and drift analysis.

Memory timeline with pagination
Point-in-time snapshots
Memory lifecycle tracking
Before/after diffs
Counterfactual recall
Drift analysis
Explore Replay →

Production-ready from day one

p50: <100ms

Median recall latency

p95: <200ms

95th percentile recall

Up to 99.9%

uptime SLA

Your data is yours — export anytime, no lock-in.

Safety & reliability built in

Execution Traces

RSA-4096 signed record of every agent step. Independently verifiable proof of what your agent did and why.

Circuit Breaker

Automatic protection against runaway loops, data exfiltration, and suspicious operations. Free on every plan.

Anomaly Detection

Behavioral baselines detect unusual agent activity. Get alerted before users notice.

Conflict Resolution

Vector clocks handle concurrent writes. Last-write-wins, reject, or flag for manual review.

What developers are building

Cross-Session Recall

A scheduling agent that auto-recalled a contact's timezone and meeting preferences in a brand new session — without being told.

30-Second Recovery

An agent that stored bad data for 3 days. One rollback command. 30 seconds. Clean state.

Ready to try it?

Free tier. No credit card. Start in 30 seconds.

Start Free

Enter your email to create your developer account.

See pricing →