/01
You ask
A task, in plain words, from the desktop app, the terminal or Telegram.
AI Research Agent
It searches the web, reads your files, and writes a report with sources.
or install from the terminal
Atomic Agent 
Hermes Agent
GAIA Level 1 – 53 real-world tasks on the same model and same machine
Accuracy · GAIA Level 1
Atomic Agent 
Hermes Agent +11.3pp More accurate
37/53 solved. Grammar-constrained decoding (GBNF) forces structurally-valid tool calls; bounded tails keep reasoning on-budget.
1.6× Faster per task
217s vs 351s. cache_prompt + slot_id reuse across steps, plus parallel read-only batches that overlap I/O after a single inference.
15 vs 9 Often right
Grammar-locked actions and step-by-step checks mean Atomic Agent rarely walks into an unrecoverable wrong answer.
how it works
↻ the loop repeats – KV-cache keeps each step cheap, nothing re-sent to a server
/02
Local model decides
One pass on your own GPU returns a list of next actions — grammar-locked, always valid.
/03
It runs them
Browser, files and shell — in parallel. Pauses for approval on risky steps.
/04
Repeat → done
Loops with cached context, so each step stays fast — until it replies or you stop it.
Questions or feedback? Grab 15 minutes with the team, any slot works.
Book a callfeatures
the engineering that keeps it fast, private, and running on your own machine
A byte-stable prompt prefix means every turn reuses the same cached compute. Nothing is re-encoded, and inference stays on your own hardware.
prefix ▓▓▓▓▓▓▓▓▓▓ cachedtail ░░░ re-computed────────────────────step N KV-cache HIT ✓
Grammar-constrained decoding forces structurally valid actions, even from tiny local models. How GBNF tool calling works
root ::= "[" call ("," call){0,15} "]"call ::= { "tool":…, "args":{…} }
Curated Q4 GGUF quants fit a long window on an everyday GPU.
fp16 ████████ ~24 GBq4 ██ ~6.7 GB
Recall injected in the tail, a few hundred tokens, cache intact.
SELECT content FROM memories_fts ORDER BY rank→ ~320 tokens
It pulls the backend and model for you. No accounts, no bills.
$ atomic-agent models startchat: started, healthy● on port 8080
Use cases
INV
IMG
ZIP
- Scanning ~/Downloads · 318 files
- Reading docs for real titles
- Grouping → /Invoices /Shots
- Renamed 212 · deduped 7
files, folders, done Sorts, renames, groups, and cleans your files — reading each one to understand it first.
BTC/USD64,210 ▲
NEWS llama.cpp v0.5 ships
MATCHARS 1–1 CHE
→ @you
- Cron · every 30m
- BTC $63,420 (+2.1%)
- Arsenal 2–1 · 78’
- Pinged Telegram ✓
cron in, Telegram out Schedule a recurring check — markets, news, match scores — and get a Telegram ping only when something changes.
acme/api main
cloning…
#42 NullRef on init
PR #128
- Cloning acme/api
- Reading issue #214
- Found in loader.go:88
- PR fix-214 ready ✓
issue in, PR out Clones a repo, reads an issue, finds the cause in the code, and opens a fix on a branch — pausing before it pushes.
wikiarxiv.org
PDF
note.md source: arxiv ✓ saved to memory
- Browsing 6 sources
- Parsing 2 PDFs
- Extracting · 12 cites
- Note saved · searchable ✓
browse, read, save Drives a real browser across sources, reads PDFs and pages, and writes a cited note into your local memory.
any model, local or cloud
Atomic Agent on OpenRouter Real production traffic: teams run Atomic Agent against cloud models through OpenRouter.
Total tokens 72.9M
Models used 32
Active since May 2026
Get new releases
by email
The desktop app is out for Mac, Windows and Linux. Download it here, then leave your email and we'll tell you when a new version ships.
EMAIL ADDRESS
FAQ
AI research agent, answered.
-
What is an AI research agent?
An AI research agent is an assistant that answers a question by actually searching, opening and reading sources, then writing up the findings with links, instead of answering from its training data alone.
-
Does web search need an API key?
No. Atomic Agent has built-in web search that works without a key, with a fallback engine. You can still connect other search tools through MCP.
-
Can it research my own documents?
Yes. It reads PDFs, spreadsheets, Markdown and other files on your disk and can combine them with web sources in one report.
-
Is a local model good enough for research?
For short questions, yes. For long research with many sources, a cloud model is noticeably more reliable. Fusion mode lets a cloud model plan while a local model does the reading.
-
How is this different from Manus or ChatGPT deep research?
Those run in the vendor cloud on credits or a subscription. Atomic Agent runs on your computer, is open source and free, can use your local files directly, and lets you pick the model. On long autonomous tasks the cloud services are usually stronger.