AI/ML●●●Banger
YantrikDB – persistent memory for AI agents
Bundled 7MB embedder means zero network calls or model downloads for agent memory.
Zero to OneWizardrySolve My Problem
pranabsarkar
111mo ago
Back to browse
GitHub Repository
Cognitive memory database for AI agents — consolidates duplicates, detects contradictions, fades stale memories via temporal decay. Rust, AGPL, ships as library / MCP server / HTTP cluster.
161 starsRust
A memory database that forgets, consolidates, and detects contradiction
by pranabsarkar·Apr 14, 2026·48 points·33 comments
AI Analysis
●●●BangerBig BrainZero to OneWizardry
Vector DBs store memories; this one forgets, consolidates, and flags contradictions like human memory.
Strengths
- •Temporal decay with configurable half-life lets unimportant memories fade automatically.
- •Contradiction detection surfaces incompatible facts before they corrupt agent reasoning.
- •Consolidation collapses duplicate memories—20 fragments become 5 canonical entries.
Weaknesses
- •Alpha stage with author as primary user—needs more real-world deployment validation.
- •AGPL license may limit enterprise adoption compared to permissive alternatives.
Category
Target Audience
AI agent developers building long-term memory systems
Similar To
Pinecone · Weaviate · Chroma
Post Description
Vector databases store memories. They don't manage them. After 10k memories, recall quality degrades because there's no consolidation, no forgetting, no conflict resolution. Your AI agent just gets noisier.
YantrikDB is a cognitive memory engine — embed it, run it as a server, or connect via MCP. It thinks about what it stores: consolidation collapses duplicate memories, contradiction detection flags incompatible facts, temporal decay with configurable half-life lets unimportant memories fade like human memory does.
Single Rust binary. HTTP + binary wire protocol. 2-voter + 1-witness HA cluster via Docker Compose or Kubernetes. Chaos-tested failover, runtime deadlock detection (parking_lot), per-tenant quotas, Prometheus metrics. Ran a 42-task hardening sprint last week — 1178 core tests, cargo-fuzz targets, CRDT property tests, 5 ops runbooks.
Live on a 3-node Proxmox homelab cluster with multiple tenants. Alpha — primary user is me, looking for the second one.
Similar Projects
AI/ML●●●Banger
Sigma Guard – deterministic contradiction checks for graph memory
Applies sheaf cohomology to catch graph contradictions that schema validation misses.
Big BrainWizardryNiche Gem
invariantjason
301mo ago
AI/ML●●●Banger
Memory system for AI agents with associations, forgetting, synthesis
Biologically-inspired memory consolidation that prunes unused facts and strengthens associations overnight.
Big BrainNiche Gem
jari_mustonen
201mo ago
Developer Tools●●●Banger
Ember MCP – local persistent memory for LLMs, kills stale memories
Temporal memory with contradiction detection—Claude finally remembers job changes.
Big BrainSolve My ProblemZero to One
TimoLabs
103mo ago
Developer Tools●●Solid
Aethene – Open-source AI memory layer
Memory deduplication and contradiction detection, but vector DBs already do semantic search.
Solve My ProblemShip It
akhilponnada
203mo ago
AI/ML●●●Banger
Claude-engram – Brain-inspired persistent memory, runs inside Claude.ai
Hippocampal memory model for Claude runs entirely in-browser, no API—genuinely novel architecture.
Big BrainZero to One
mlapeter
623mo ago