HN Showcase
Back to browse
Novyx – Memory API for AI agents (rollback, replay, semantic search)

Novyx – Memory API for AI agents (rollback, replay, semantic search)

by blakeheron·Feb 26, 2026·1 point·0 comments
Visit ProjectView on HN

AI Analysis

●●SolidSolve My ProblemBig Brain

Git-for-agent-state rollback with tamper-proof audit logs; solves real agentic memory failure modes.

Strengths
  • •Rollback + cryptographic audit trail solves genuine pain (the founder's story is credible and specific)
  • •Recency-weighted semantic recall + knowledge graph auto-dedup is more sophisticated than naive vector search
  • •Time-travel debugging via replay lets developers understand agent decisions, not just undo them
Weaknesses
  • •Memory APIs for agents is still nascent; unclear if market exists yet or will consolidate into framework stacks (LangGraph, etc.)
  • •No independent benchmarks vs. vector DBs + lightweight persistence; claims like 'sub-100ms recall' lack context
Category
AI/ML
Target Audience

AI agent developers, autonomous system builders, enterprises running multi-session agents

Similar To

LangGraph memory modules · Mem0 (agent memory platform) · Weaviate (knowledge graph + semantic search)

Post Description

Hey HN — Blake here. We built Novyx because every AI agent framework treats memory as an afterthought. Agents forget between sessions, can't search what they know, and when they make bad decisions there's no way to understand why.

Novyx is a memory API for AI agents. Store observations, recall them with semantic search, and roll back when things go wrong.

What it does:

- Store + Recall — Semantic search over agent memories using sentence embeddings. Recency-weighted scoring, auto-linking related memories via knowledge graph. - Rollback — Point-in-time rollback with dry-run preview. Undo bad writes without redeploying. - Replay — Time-travel debugging. Reconstruct what your agent knew at any timestamp. Diff memory states between two points. Track individual memories from birth to death. - Cortex — Autonomous memory maintenance. Consolidates near-duplicate memories, reinforces frequently recalled ones, decays forgotten ones. Runs in the background. - Audit trail — Compliance-grade logging of every memory operation. Tamper-evident hash chains.

Technical details:

- Postgres + pgvector for storage and search. Redis for auth/rate limiting. CPU-only embeddings (all-MiniLM-L6-v2). - Multi-tenant with application-level isolation. ~82 REST endpoints. - Python SDK and JS/TS SDK. LangChain, CrewAI, and MCP integrations. - Free tier: 5K memories, 5K API calls/mo. Pro ($39/mo): unlimited memories + Replay + Cortex. Enterprise ($199/mo): counterfactual recall, drift analysis, insights.

We're not competing with LangSmith or Langfuse — those are trace debuggers (what the LLM said). We're the layer underneath (what the agent knew).

Live at https://novyxlabs.com. Docs at https://novyxlabs.com/docs.

Happy to answer questions about the architecture.

Similar Projects