EverOS: Putting the Pieces Together to Find Loved Ones A face, a place, a small detail someone still remembers. When you’re searching for a loved one, those fragments can mean so much. ReUnite is a nonprofit project built with EverOS and an award-winning use case from the Memory Genesis competition 2026. It brings scattered pieces of memory together to help people search for their loved ones. We’re deeply moved by what this team is building. Seeing our community use EverOS for something so human means a great deal to us.

EverOS v1.5.1 is here. A small open-source update for a frustrating problem: memory searches queuing up under load. We increased the default query-embedding concurrency from 4 to 16, giving hybrid and vector search more room to handle concurrent requests. In our five-minute test with 10,020 indexed entries at 10 requests per second: • p95 latency dropped from 101s to 1.45s • All 3,000 requests were served No migration needed, just upgrade. If your embedding endpoint has tight rate limits, tune the concurrency to match. Prefer to build without managing the infrastructure? EverOS Cloud brings managed memory to your existing agent workflows. Save useful context after a task, retrieve it before the next, and give your agents access to user preferences, business knowledge, and past experience through APIs. Start with one recurring workflow and let useful context accumulate across runs. Subscribe to EverOS Cloud Pro now and get 3× the standard monthly usage for your first 3 months. Cloud:

EverOS open-source v1.4.2 is here. This release tackles problems that show up when memory servers keep running: • Fixed a file-descriptor leak in long-lived indexes • Separated query embeddings from background writes, so searches don’t queue behind ingestion • Fixed cross-project index overwrites, your Markdown memories were never affected Upgrade: pip install --upgrade everos Check the release notes before upgrading: Milvus and certain multi-project deployments require an index rebuild. Prefer managed memory infrastructure? Build with EverOS Cloud.

EverOS is now a @convex-dev component. 🧠 Add persistent long-term memory to any Convex app, or to @convex-dev/agent in one line, backed by EverOS Cloud. Convex already gives agents the backend primitives they need: a reactive database, durable functions, scheduling, and threads. Now agents can remember across threads and sessions too. EverOS turns conversations into durable user memory: facts with timestamps and traceable sources, plus a profile that evolves over time. That memory belongs to the user and follows them across threads, sessions, models, and agents. Under the hood, EverOS delivers state-of-the-art results across long-term memory benchmarks. No vector database to run. No memory infrastructure to stitch together. Get it today:

EverOS 1.3.1 is here. The multi-round retrieval we just shared is now available in EverOS: let the model decide what evidence to keep, what to search next, and when to stop. Also in this release: • One reproducible runner for four memory benchmarks: LoCoMo, LongMemEval, EverMemBench, and SubtleMemory • A separately configurable retrieval decider • Better timeout handling, retry behavior, and database diagnostics • No storage migration or index rebuild required. Multi-round retrieval is opt-in.

EverOS 1.3.0 is out. You can now use @milvusio or Zilliz Cloud to index your agent’s memory. LanceDB remains the default. Markdown remains the source of truth. Switching backends means rebuilding the index from your memory files. Already running Milvus? EverOS now fits into your stack. Thanks to everyone testing, reporting bugs, and contributing.

EverOS v1.1.1 is live. A small release focused on measurable memory quality: • LoCoMo benchmark runner + docs • Hybrid search optimization (~91% stable) • Agentic search benchmark (~93% stable) • Knowledge cascade upsert race fix • Python 3.12/3.13 CI

EverOS just crossed 9,000 GitHub stars.🎉 The response to our 1.0.0 -> 1.1.0 release means a lot, especially the interest in Knowledge Wiki and Reflections. Thank you to everyone sharing the repo and supporting us. We will keep building agent memory and agentic infra. Thank you. Stay tuned.

In case you missed it: EverOS open-source v1.4.1 The 1.4 series brings native Windows support, faster memory retrieval, and more reliable indexing. The v1.4.1 patch fixes a dependency issue affecting fresh installs. Building an agent that needs to remember users, retrieve past context, and reuse lessons from previous tasks? EverOS Cloud provides managed memory through an API, with support for conversations, images, and documents. We handle the memory infrastructure so you can focus on your product. Start building for free:

From 8,594 tokens to 1,946 per answer. EverOS selects the memories a question actually needs instead of injecting a fixed 20 every time. In our LongMemEval-S test, that meant 77% fewer answer-stage input tokens, with 91% accuracy versus 93.4%. Less context to process. Relevant evidence to work with.