Skip to main content

Search2o: a platform to build, run, and use AI agents, with a search interface

Website: search2o.com · Source: GitHub · GUI source: GitHub · Docs: search2o.com/docs . Skill Search2o-skill

This repository contains the Search2o Agent Server: a stateless, asynchronous Python server that runs agents inside your organization, with a REST API and a bundled GUI. Search2o is in open beta.

Getting started

1. Create your account

Create your account at Getting started. Your license key appears on that page when the account is created. No email is sent at this step.

2. Install the agent server

Install the agent server with the bundled GUI:

pip install search2o

This GitHub repository holds the agent server without the GUI; the GUI source is at github.com/Search2o/ui.

3. Run the server

macOS / Linux:

SEARCH2O_LICENSE_KEY=your-license-key search2o

Windows PowerShell:

$env:SEARCH2O_LICENSE_KEY="your-license-key"
search2o

Self-hosted models using Ollama, vLLM or SGLang need no vendor API key. For OpenAI, Anthropic or Gemini, before starting the server, also set one or more of OPENAI_API_KEY, ANTHROPIC_API_KEY or GEMINI_API_KEY. For other LLMs, see Connecting to other LLMs.

4. Set up your account

Open http://127.0.0.1:9020/ui and click New user / Forgot password on the sign-in dialog. Enter the same email you used to create your account in step 1. A code is emailed to that address and no other. Enter the code, choose a password, and sign in.

The server also serves its OpenAPI schema at /openapi.json, Swagger UI at /docs and ReDoc at /redoc.

5. Build your first agents

LLMs are called from an agent using an LLM profile. You can use an existing profile or create a new one.

  1. Open Agents → Drafts and create a draft. Select your LLM profile, then tell Draft with AI what you want.
  2. Build two or three task-specific agents. Each agent would typically use one or two of your enterprise systems and handle a specific use case.
  3. Validate and publish them. Then add plain-English descriptions so search can find them.
  4. Type a question in the search box: the agent matches, runs and answers.

The same agents work in Claude Code through the search2o-skill.

If you have questions, click the docs icon at the top of the UI, or see the full documentation at search2o.com/docs. We would love to hear how setting up and running your first few agents went: email info@search2o.com, or send a message from the message icon in the GUI.

License

The Search2o Agent Server is source available and proprietary. Use is subject to the Search2o Software License Agreement.

Contributions

External code contributions and pull requests are not currently accepted. Bug reports, feature requests, documentation feedback, and security reports are welcome. See CONTRIBUTING.md.

Metadata

Release files for search2o 0.11.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for search2o 0.11.1
File Size Uploaded
search2o-0.11.1.tar.gz 6.5 MB Details

Built distribution (wheel)

Table of built distributions (wheels) for search2o 0.11.1
File Interpreter ABI Platform
search2o-0.11.1-py3-none-any.whl Python 3 none any Details

Total release size: 13.2 MB

Release files / search2o-0.11.1.tar.gz

Download URL search2o-0.11.1.tar.gz
Size 6.5 MB
Tags Source
SHA-256 checksum
How to use checksums
479cb5fdcf59c95469b7f69c05c98c7370fc42b983ab86ba6bfe2136fc8145a1
BLAKE2b-256 checksum
How to use checksums
890a87f2c01bf6fe075e6d520fadf57b3f8b9e34d97f91edbfeaa9e57291d6f1
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.12.10

Release files / search2o-0.11.1-py3-none-any.whl

Download URL search2o-0.11.1-py3-none-any.whl
Size 6.7 MB
Tags Python 3
SHA-256 checksum
How to use checksums
56d0361b2e2fca85428c0eeed1affe60c79895b3893de6799bca2a517284f721
BLAKE2b-256 checksum
How to use checksums
c031d44f623408d0dfb68634ba652acb3a868389c7576f9cc60ee7141c6a2f82
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.12.10

Release history Release notifications | RSS feed

This release

0.11.1 This release

2 release files

0.9.3

2 release files

0.9.2

2 release files

0.9.1

2 release files

0.9.0

2 release files

0.8.0

2 release files

0.7.4

2 release files

0.7.3

2 release files

0.7.2

2 release files

0.7.1

2 release files

0.7.0

2 release files

0.6.2

2 release files

0.6.1

2 release files

0.6.0

2 release files

0.5.1

2 release files

0.5.0

2 release files

0.4.1

2 release files

0.4.0

2 release files

0.3.4

2 release files

0.3.3

2 release files

0.3.2

2 release files

0.0.1

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page