v2.9.1Reliability
Platform Stability & Account Management Improvements
Improved account provisioning reliability, API gateway stability, and expanded sandbox limits for enterprise users.
- Improved new account onboarding: subscriptions and roles now provisioned automatically on all signup flows
- API gateway routing improvements for faster, more reliable endpoint resolution
- Sandbox environment limits expanded for Pro and Enterprise plans
- Enterprise dashboard now displays accurate storage usage metrics
- Content Security Policy updates for improved third-party integration support
v2.9.0Platform
Dashboard Enhancements & Developer Tools
Comprehensive dashboard improvements across Sessions, Storage, AI Usage, Earnings, and MCP Hosting pages with real-time data integration.
- Sessions page: view and manage AI conversation sessions with memory context and statistics
- Storage page: streamlined project selection and improved file upload experience
- AI Usage dashboard: enhanced charts for model usage, daily trends, and cost breakdown
- Developer Earnings: full earnings overview, transaction history, and payout scheduling
- MCP Hosting: improved server deployment flow and instance management
- ZeroMemory API: new endpoints for remember, recall, reflect, and knowledge graph operations
- Documentation: updated API Reference links and Getting Started guide
- Events page: added conversion tracking for marketing campaigns
v2.8.5Knowledge Graph
Context Graph: GraphRAG & Knowledge Graph for ZeroDB
New knowledge graph capabilities for ZeroDB with ontology-aware entity resolution, edge versioning, and graph templates for common use cases.
- Context Graph API: create entities, edges, and traverse relationship chains
- GraphRAG: hybrid vector + graph search for more accurate retrieval
- Knowledge Graph visualization in the ZeroDB Console
- Graph templates for common patterns: user profiles, project dependencies, agent memory
- Ontology support with edge versioning for structured knowledge representation
v2.8.2ZeroMemory
ZeroMemory Recall Improvements & Benchmarks
Enhanced vector similarity search in ZeroMemory with improved scoring accuracy and richer recall results for AI agents.
- Vector similarity search integrated into ZeroMemory remember and recall flows
- LongMemEval benchmark suite for measuring long-term memory retrieval quality
- Improved memory scoring accuracy for temporal decay and recency weighting
- Recall results now include full metadata for richer agent context
- ZeroDB namespace management improvements and auto-provisioning
v2.8.0Enterprise
Enterprise Security Suite & Audit Improvements
Major enterprise-grade release with expanded security controls, audit logging enhancements, and compliance reporting.
- AX audit logging now captures full request context, including IP, user agent, and session metadata
- New compliance dashboard for SOC 2 and GDPR audit trails in the admin panel
- Role-based access control (RBAC) expanded with fine-grained scopes for API key management
- Organization-level SSO improvements: SAML 2.0 and OIDC providers now support JIT provisioning
- Audit export API added — export structured logs in CSV or JSON for external SIEM systems
v2.7.5ZeroMemory
ZeroMemory v2: Cognitive Memory for AI Agents
ZeroMemory now supports semantic recall, temporal decay scoring, and graph-based memory relationships — giving agents persistent, intelligent memory across sessions.
- New `/memory/v2/recall` endpoint with hybrid vector + keyword retrieval
- Temporal decay scoring: memories naturally deprioritize over time unless reinforced
- Memory graph API: relate memories to entities and traverse relationship chains
- Reflection endpoint: agents can summarize and compress past memories into condensed knowledge
- Profile endpoint for per-user and per-agent preference storage
- Improved cross-collection memory lookups for multi-agent environments
v2.7.0New
Webhook Event Dispatcher
Platform-wide webhook delivery system for real-time event notifications on agent runs, memory updates, and billing events.
- Webhook endpoints configurable per organization from the developer settings dashboard
- Delivery retries with exponential backoff (up to 5 attempts)
- Event types: agent.run.completed, memory.stored, billing.credit.low, api.key.created
- HMAC-SHA256 payload signing for secure delivery verification
- Webhook delivery logs available in the developer dashboard for the past 30 days
v2.6.8SEO
Discovery & SEO Alignment
Improved discoverability across the platform and ecosystem documentation.
- Updated llms.txt and agents.txt with ZeroMemory capabilities for AI crawler indexing
- Added security.txt following RFC 9116 for responsible disclosure
- Sitemap regeneration with priority weighting for product pages
- Structured data (JSON-LD) expanded across product and documentation pages
v2.6.5Developer Program
Echo Developer Program: Usage-Based Revenue
Developers can now monetize their apps built on AINative APIs through the Echo Developer Program.
- Set markup (0–40%) on API usage by your end users
- AINative takes a flat 5% platform fee on all developer earnings
- Stripe Connect integration for weekly automated payouts (minimum $10)
- Earnings dashboard with per-app and per-user usage breakdowns
- New React SDK hooks: useChat and useCredits for easy integration
- Next.js SDK with server client and auth middleware for SSR apps
v2.6.0ZeroDB
ZeroDB File Storage (S3-Compatible API)
ZeroDB now includes an S3-compatible object storage layer for agent-accessible file management.
- PUT, GET, DELETE file operations via REST API
- Presigned URL generation for direct browser uploads
- Per-user and per-organization storage quotas
- Files indexed for semantic search alongside vector embeddings
- MCP tool integration: agents can read and write files via the ZeroDB MCP server
v2.5.3Performance
Embedding Service: 16ms Inference
The embedded text embedding service has been re-architected around TEI (Text Embeddings Inference) for drastically reduced latency.
- Average embedding inference down to 16ms from ~120ms
- Batch embedding endpoint now supports up to 512 texts per request
- New model: nomic-embed-text-v2-moe for higher-quality retrieval
- Automatic model warm-up on cold starts to eliminate first-request latency spikes
v2.5.0Security
API Key Scoping & Expiry Controls
API keys can now be scoped to specific permissions and configured with automatic expiry dates.
- Scoped keys: limit keys to specific endpoints (e.g., memory:read, embeddings:write)
- Key expiry: set keys to expire after a defined number of days or on a specific date
- Last-used tracking: see when each key was last authenticated
- Key rotation endpoint: rotate a key without downtime by generating a successor key
