CURRENT RELEASE · v0.1.24 · LOCAL ONLY

The verified state of AI Agents Lab v0.1.24.

Public BETA download: The v0.1.24 Windows ZIP is available without GitHub sign-in. SHA-256: 3a791b964584d00994a737b0d84796f122fe47c3f911a3045d6bdccd1ad47db1.

Download AI-Agents-Lab-Windows.zip (v0.1.24) Read the current-state guide

AVAILABLE IN v0.1.24

Local Agent Training

Using Ollama on the same device, the Learning Lab runs the released sequence: Trainer → Student → Evaluator → Improver. It is local-only and requires a running local Ollama model.

UNDER CONSTRUCTION

Agent Collaboration / Conference Room

The released interface keeps this room disabled. Planner, Researcher, and Reviewer code exists, but the feature is not available to users in v0.1.24.

NOT YET OPERATIONAL

Advanced model fine-tuning

Optional parameter fine-tuning is not operational in v0.1.24. Its training worker has a confirmed compatibility issue that must be resolved before it can be presented as available.

NOT IMPLEMENTED

Manual update check in the Local App

The released Local App has no in-app update checker. A future manual check must be explicitly implemented and must never download or install updates automatically.

SUPPORTED PROVIDER

Ollama only

The released Local App connects only to Ollama at its fixed loopback address. LM Studio and vLLM are not supported inference providers in v0.1.24.

LOCAL INFERENCE PROVIDER

Use Ollama for this release.

REQUIRED FOR INFERENCE

Ollama

A local runtime for Windows, macOS, and Linux. AI Agents Lab v0.1.24 uses only Ollama at 127.0.0.1:11434.

Download Ollama

INSTALLATION STATUS

Install the public BETA release.

  1. Download the official ZIP. Use the public BETA download above; GitHub access is not required.
  2. Verify and extract the ZIP. Confirm the displayed SHA-256 checksum, then extract it to a folder you control, such as Documents\\AI-Agents-Lab. There is no hidden installation folder: this extracted folder is the Lab.
  3. Install Python and Ollama. Install Python 3.9 or later for Windows, then install Ollama from the official link above.
  4. Run a local Ollama model. For example, run ollama pull qwen3:4b; the Lab uses Ollama only at 127.0.0.1:11434.
  5. Keep Ollama local-only if you use it. Add "disable_ollama_cloud": true to %USERPROFILE%\.ollama\server.json, preserving any existing settings, then restart Ollama. Use downloaded local models, not names ending in :cloud.
  6. Start the local server from the extracted ZIP folder. Open start-windows.bat in that extracted folder (or run py -3 server.py there) and keep its window open. Its first run creates a Desktop shortcut that continues to open this extracted copy.
  7. Only after the local server has started, open the local address. When the start-windows.bat window confirms that the Lab is running, select Open Local Lab. The link cannot start the Lab by itself.

Updates — current state: The Local App in v0.1.24 has no manual in-app update check. If an authorized newer ZIP is provided, update manually: stop the Lab, back up data/campus.sqlite3, extract the new ZIP to a new folder, and start that copy once to refresh the Desktop shortcut.

PRIVACY

This site does not run the Lab.

There is no sign-in, chat input, model endpoint, telemetry, or personal-data collection on this Pages site. The current release is a local package and connects only to local Ollama.