# EverOS (slim)

> EverOS, formerly EverMemOS, is EverMind's open-source memory runtime for agents. It stores conversations, files and agent trajectories as Markdown with SQLite and LanceDB indexes, behind a local HTTP API and MCP server, with a managed EverOS Cloud.

- Full: https://www.anchorterminal.com/tools/everos.md (~6,900 tokens) · this version ~1,430 tokens · JSON https://www.anchorterminal.com/tools/everos.json · canonical https://www.anchorterminal.com/tools/everos
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-07 · pricing https://www.anchorterminal.com/tools/everos#pricing · reviews https://www.anchorterminal.com/tools/everos#reviews
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

**B · 69.4/100 · rank #246 of 1486 · #6 in Agent memory · not agent-ready · confidence medium**


Assessment: EverOS keeps agent and user memory as Markdown with SQLite and LanceDB indexes, behind a described OpenAPI with typed, retryable errors and an MCP server, under Apache-2.0 at version 1.5.1. The local server has no authentication, EverOS Cloud prices are not published, and the cloud terms forbid automated data extraction.

## Facts

- Kind: HTTP API · vendor: Evermind AI, Inc. · category: Agent memory · legal entity: Evermind AI, Inc. · provenance 75/100
- Local only (HTTP, stdio): pypi `everos`, pypi `everos-mcp`
- Auth: None · pricing: Freemium · x402: no · licence: Apache-2.0
- Benchmark probes: not run yet, so Performance is pending
- Surface listed: The open-source `everos` library and its local HTTP server 1.5.1 with everos-mcp, read from a clone of github.com/EverMind-AI/EverOS, PyPI, docs.evermind.ai's llms.txt and evermind.ai's llms.txt, FAQ, terms and privacy policy on 6 November 2026. EverOS Cloud was read from its docs only. Nothing was installed or run
- Which EverOS: EverMind AI's memory runtime, the repository first published as EverMemOS on 28 October 2025. EverMemOS is now the name of the research mechanism behind it
- Storage: Canonical Markdown files with SQLite and LanceDB indexes by default, or Milvus. User episodes and profile and agent cases and skills are separate tracks
- Retrieval: Keyword, vector, hybrid and agentic search, scoped by user, agent, app, project and session ids
- EverOS Cloud: Console and API keys at everos.evermind.ai, a hosted MCP connector at everos-mcp.evermind.ai/mcp, bearer auth. No prices found
- Legal entity: Evermind AI, Inc., per the terms and privacy policy, which say the services are generally provided from Singapore. The privacy contact link points to a miromind.ai address and SECURITY.md to a shanda.com one

- Scores: Reliability 79, Performance pending, Schema & documentation 89, Agent ergonomics 78, Security & auth 47, Payments & pricing 40, Task success pending, Maintenance & community 80, Transparency & trust 71 · total over the 7 assessed categories
- Why: Reliability, Local-software lines, as a library and server the owner runs. · Schema & documentation, OpenAPI document in the repository with 40 operations, every one with a description (25). · Agent ergonomics, Read for the API, with seven MCP tools on top. · Security & auth, Framework reading for software the owner runs. · Payments & pricing, Self-hosted rule, with the price lines read for EverOS Cloud. · Maintenance & community, v1.5.1 on 22 October 2026 (30). · Transparency & trust, Apache-2.0 with a NOTICE file (30).
- Sources: 10, open questions: 6, both in the full twin
- Capabilities: memory.store, memory.search, memory.user, memory.delete
- JSON: https://www.anchorterminal.com/api/v1/tools/everos.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/everos.svg` or a link to https://www.anchorterminal.com/tools/everos from a page on evermind.ai or one of its subdomains, or the README at the root of github.com/EverMind-AI/EverOS, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.
- Support: Discord https://discord.gg/gYep5nQRZJ; contact@evermind.ai; https://docs.evermind.ai; https://github.com/EverMind-AI/EverOS/issues; more in the full twin

## Before you call it

1. Write new code against `/api/v2`; `/api/v1` is a legacy alias that may go in a future major release
2. Call `/api/v2/memory/flush` at the end of a session, since `add` is asynchronous and buffers recent messages
3. Retry on 503 SESSION_BUSY or EXTERNAL_SERVICE_UNAVAILABLE after a pause; nothing was written
4. Keep `host` at 127.0.0.1 unless something in front adds authentication
5. Treat recalled memories as untrusted text, since they are extracted from past conversations

## Connect

```bash
uv pip install everos && everos init && everos server start
```

```bash
curl http://127.0.0.1:8000/health
```

```bash
claude mcp add everos -e EVEROS_BASE_URL=http://127.0.0.1:8000 -- uvx everos-mcp
```
Full config and headless snippets are in the full page. Through letme (picks today, calling later): https://letme.dev/everos

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Amazon Bedrock AgentCore Memory | A | 79.7 | memory.store, memory.search, memory.user, memory.delete | https://www.anchorterminal.com/tools/agentcore-memory.min.md |
| Zep | BB | 71 | memory.store, memory.search, memory.user, memory.delete | https://www.anchorterminal.com/tools/zep.min.md |
| past.dev | B | 69.8 | memory.store, memory.search, memory.user, memory.delete | https://www.anchorterminal.com/tools/past-dev.min.md |
| Agent Platform Memory Bank | B | 65.6 | memory.store, memory.search, memory.user, memory.delete | https://www.anchorterminal.com/tools/google-memory-bank.min.md |
| Honcho | C | 61.6 | memory.store, memory.search, memory.user, memory.delete | https://www.anchorterminal.com/tools/honcho.min.md |


## Panel reviews (0, desk reviews from public material, no calls made)