MemoryOS
AI agent memory with knowledge graph and 78ms retrieval
MemoryOS launched on May 12, 2026.
What it does
Most AI memory tools either score badly or cost $249/mo. So I built MemoryOS — an open-source, self-hosted memory layer for AI agents. Benchmarks (LongMemEval-s, ICLR 2025): • HydraDB - 90.79%, <200ms - $249/mo • Supermemory - 85.4%, <300ms • MemoryOS - 86.2%, 78ms - free open source Features: * Temporal knowledge graph with point-in-time memory * Hybrid retrieval: vector + BM25 + graph traversal * Human-inspired memory decay * 9ms/msg ingest pipeline * Fully local retrieval hot path
AI agent memory. Temporal knowledge graph + hybrid vector retrieval + Ebbinghaus decay. 78ms queries, 9ms/msg ingest. - Per0x1de-1337/MemoryOS
Open-source memory layer for AI agents. Gives your agents persistent, queryable memory across conversations with temporal awareness, a knowledge graph, and sub-100ms retrieval. User: "What degree did I graduate with?" Agent: [searches 550 messages in 79ms] → "Business Administration" Features Persists facts across sessions, not just the last N messages Tracks how facts change over time ("Alice lived in Boston in 2022, moved to Seattle in 2024") Append-only graph: old facts are superseded, never deleted Every retrieval includes a score breakdown and reasoning trace Ebbinghaus-based decay keeps the index clean over time Performance Measured on Azure D48ads-v5 (48 vCPU, no GPU): Requirements:…from github.com
Does a similar job
all alternatives →
DeltaMemoryFeb 2026 · deltamemory.com · ▲104Most AI agents forget everything between sessions. We built DeltaMemory to fix that. It's a cognitive memory layer that gives agents persistent recall, automatic fact extraction, and temporal reasoning — via a single SDK call. Key numbers: - 89% accuracy on LoCoMo long-term conversation benchmark - 50ms p50 retrieval latency - 97% cost reduction vs raw token re-processing Open source SDKs, works with any LLM stack. Currently in early access. Happy to answer questions about the architecture, benchmark methodology, or how we handle knowledge graphs.
AgentmemoryMay 2026 · agent-memory.dev · ▲310Persistent memory for Claude Code, Codex & coding agents
YourMemoryApr 2026 · yourmemoryai.vercel.app · ▲93This is a project that I have been building for a while now, YourMemory is a solution to agentic memory which focuses on pruning of noise rather than hoarding of data. In the current state of agentic memory most of the context is stored in the form of a MD file or is derived through a RAG model where you store each and everything. Both of the solution leads to bloated context which does not optimize the usage of any tokens. In this system we only keep relevant data in our memory and prune all the unnecessary data. The relevance of a data is derived through multiple factors such as recall…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 21d ago · stillwet.art
FastRouter.ai▲364Route requests to the right LLM for cost, latency & quality
AI · 22d ago · fastrouter.ai
Source: Product Hunt launch ↗
Launched alongside, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
🌱 Private, quiet space for thinking. Simple app for .md files. - zakirullin/files.md
Dev tools · May 2026 · github.com