EverOS is a free, open source ai development platforms project written in Python and released under Apache-2.0. It has 13,042 GitHub stars, 923 forks and 73 open issues, and was last pushed 9 days ago. On this registry it ranks #51 of 116 tracked projects in AI Development Platforms, with 5 head-to-head comparisons available.
What is EverOS?
EverOS is an Apache-2.0 Python library and local-first memory runtime that gives AI agents and their builders one portable, Markdown-native memory layer spanning coding assistants, apps, devices, and workflows.
What it is
EverOS is a Python library and memory runtime for agents and makers. It stores conversations, files, and agent trajectories as readable Markdown, then syncs local SQLite and LanceDB indexes so retrieval stays fast and memories can be reused and evolved across sessions. It lives in the agentic AI and agent-memory corner of the Python ecosystem, and ships with integrations for DeepSeek Harness, Hermes, OpenClaw, and Dify, alongside Raven, where it comes built in.
The concrete thing it replaces is whatever ad hoc memory each assistant, app, or workflow invents on its own: chat history buried in a proprietary store, vector or graph database state that a person cannot read or diff, or a dashboard that owns the memory rather than the user. EverOS makes the Markdown files the canonical source of truth, so memory can be opened in an editor, committed to Git, and carried between tools instead of being trapped behind a single vendor's API.
Key capabilities
Markdown as the canonical source of truth: .md files that are readable, editable, diffable, and Git-versionable.
Direct file editing with a cascade watcher, so changes made by hand in the Markdown sync back into the indexes.
A local three-part stack of Markdown, SQLite, and LanceDB, with no MongoDB, Elasticsearch, or Redis required.
Separate first-class user and agent tracks: user episodes and profiles alongside agent cases and skills.
Orthogonal retrieval filtered by user_id, agent_id, app_id, project_id, and session_id.
A Knowledge Wiki of editable, source-backed Markdown pages with taxonomy, CRUD APIs, and topic search.
Reflection, an offline evolution pass that merges episode clusters and refines profiles and skills between sessions.
Who uses it and how
Individual makers running coding assistants locally who want one memory that follows them across apps, devices, and workflows.
Teams already on an integrated platform such as Raven, where EverOS is built in and needs no separate deployment.
Builders wiring durable memory into DeepSeek Harness, Hermes, OpenClaw, or Dify through the documented integration guides.
Users who want to inspect or correct what an agent remembers by editing the underlying .md files directly.
Anyone needing long-horizon consolidation, where Reflection merges episode clusters between sessions instead of relying on retrieval alone.
Getting started
Install with uv pip install everos or pip install everos, then run everos demo for a key-free walkthrough, or everos init followed by everos server start to bring up the local server on http://127.0.0.1:8000. Tier 1 needs Python 3.12+ and one OpenRouter API key written into ~/.everos/everos.toml; business endpoints live under /api/v2.
How it compares
The facts provide no list of paid products that EverOS replaces, and they name no directly comparable tool, so it stands alone in this registry as the Markdown-native, local-first agent memory layer. The README contrasts it with other agent memory libraries generically rather than by name: those usually keep memory in API, vector, graph, dashboard, or database state, whereas EverOS keeps .md files canonical and edits cascade back through a watcher. Where those alternatives lean on managed services, vector or graph databases, or server stacks, EverOS runs on Markdown, SQLite, and LanceDB alone.
When to use it — and when not to
A self-hoster must run a local server process and keep the memory root available, and embedding and rerank remain disabled until configured, so the one-key Tier 1 setup starts with LLM-backed writes and keyword search rather than semantic retrieval. Anyone unwilling to maintain a Python 3.12+ process, or who needs a fully managed service with no local component, should look elsewhere. The README also flags that the older /api/v1 prefix is a legacy alias with an uncertain future, so new integrations should target /api/v2 from the start.
project readme (upstream, from github) — read inline
EverOS is a Python library and local-first memory runtime for agents and
makers. It gives one portable memory layer across coding assistants, apps,
devices, and workflows from day one. It stores conversations, files, and agent
trajectories as readable Markdown, then syncs local SQLite and LanceDB indexes
for fast retrieval and self-evolving reuse.
Title
EverOS
Other Agent Memory Libraries
Markdown source of truth
✅ Canonical .md files that are readable, editable, diffable, and Git-versioned
❌ Usually API, vector, graph, dashboard, or database state
Direct file editing
✅ Edit .md files; cascade watcher syncs
❌ Usually SDK, API, dashboard, or backend update paths
Local three-part stack
✅ Markdown + SQLite + LanceDB; no MongoDB, Elasticsearch, or Redis required
❌ Often depends on managed services, vector DBs, graph DBs, or server stacks
User + agent tracks
✅ User episodes/profile and agent cases/skills are separate first-class surfaces
❌ Usually centered on chat history, profiles, entities, facts, or retrieval records
Orthogonal retrieval
✅ Search by user_id, agent_id, app_id, project_id, and session_id
❌ Usually app, namespace, tenant, thread, or graph scoped
Knowledge Wiki
✅ Editable, source-backed Markdown knowledge pages with taxonomy, CRUD APIs, and topic search
❌ Usually separate from memory, trapped in a dashboard, or not tied back to source files
Reflection
✅ Offline memory evolution that merges episode clusters and refines profiles and skills between sessions
❌ Usually retrieval-only memory with little background consolidation or long-horizon improvement
Ecosystem Integrations
EverOS adds durable memory to the agent and workflow platforms below—and comes
built into Raven. Choose an integration to open its setup guide.
No API key or server setup required—run one command to quickly experience how
EverOS stores and recalls memory:
# If you installed EverOS as a package:
everos demo
# If you cloned or forked this repository and have not activated .venv:
uv run everos demo
Enter something EverOS should remember, then ask a related question to watch
the memory move through ingest -> extract -> index -> recall.
3. Initialize and add your OpenRouter key
everos init
This creates ~/.everos/everos.toml and ~/.everos/ome.toml. Open
~/.everos/everos.toml; the generated model and OpenRouter URL are already
correct, so replace only the empty api_key:
[llm]
model = "openai/gpt-4.1-mini"
api_key = "<OPENROUTER_API_KEY>"
base_url = "https://openrouter.ai/api/v1"
This is the smallest Tier 1 setup: memory add, flush, Markdown persistence,
cascade indexing, and keyword search.
Use everos init --root if you want a different memory root. Pass the
same --root to subsequent commands.
4. Start EverOS
everos server start
Keep the server running, then open a second terminal and check it:
curl http://127.0.0.1:8000/health
Look for "status":"ok". With this one-key setup, capabilities.llm is
true; embedding and rerank remain false until you configure them.
5. Add and retrieve your first memory
[!NOTE]
Business endpoints live under /api/v2. The older /api/v1 prefix still
resolves to the same handlers so existing integrations keep working, but it
is a legacy alias that may be removed in a future major release — write new
code against /api/v2.
Add a tiny conversation:
TS=$(($(date +%s)*1000))
curl -X POST http://127.0.0.1:8000/api/v2/memory/add \
-H 'Content-Type: application/json' \
-d "{
\"session_id\": \"demo-001\",
\"app_id\": \"default\",
\"project_id\": \"default\",
\"messages\": [
{\"sender_id\": \"alice\", \"role\": \"user\", \"timestamp\": $TS, \"content\": \"I love climbing in Yosemite every spring.\"},
{\"sender_id\": \"alice\", \"role\": \"user\", \"timestamp\": $((TS+10000)), \"content\": \"My favorite coffee shop is Blue Bottle in SOMA.\"}
]
}"
curl -X POST http://127.0.0.1:8000/api/v2/memory/search \
-H 'Content-Type: application/json' \
-d '{
"user_id": "alice",
"app_id": "default",
"project_id": "default",
"query": "Where do I like to climb?",
"method": "keyword",
"top_k": 5
}'
You should see the Yosemite memory in the response. Keep
"method": "keyword" in this one-key setup because the API defaults to hybrid
search, which requires an embedding provider.
[!TIP]
First memory unlocked.
You just gave EverOS a fact, flushed it into durable Markdown-backed memory,
and searched it back through the local index. That is the core loop.
Want to see the source of truth? Open ~/.everos and inspect the generated
Markdown files.
For annotated responses and the Markdown files EverOS creates, see
QUICKSTART.md.
EverOS is open source under the Apache-2.0 licence. There is no licence fee and no seat count — you can self-host it or, where the project offers one, pay a vendor for a managed version instead.
What does EverOS do?
One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
What is EverOS written in?
EverOS is primarily written in Python. Its source is publicly available at https://github.com/EverMind-AI/EverOS, and it has 13,042 GitHub stars.
