SERA (Ai2 Open Coding Agents)
Fully open developer agents from Ai2: weights, data and training recipe are all public. Designed so a company can cheaply fine-tune the agent on its own repository.
- Developer
- Ai2 (Allen Institute for AI), USA
- First release
- Jan 2026
- Latest release
- Feb 2026
- Sizes
- 8B – 32B
- License
- Commercial use allowedApache 2.0
- Russian
- Not stated
- Running
- On your own serverNeeds a GPU
- Industries
- Software development, Science and research
What it does
- An agent for fixing issues in code
- Fine-tuning the agent on an internal repository
- Automating small edits and tests
Where it is used
Hardware requirements
Versions
- SERA-14B
- SERA-8B и SERA-32B
How to run it
I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.
Frequently asked questions
Can SERA (Ai2 Open Coding Agents) be used in a commercial project?
Yes. License: Apache 2.0. It allows commercial use, but it is still worth having a lawyer review the license before launch.
What hardware does SERA (Ai2 Open Coding Agents) need?
At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.
Does SERA (Ai2 Open Coding Agents) support Russian?
The model card does not list languages, so Russian support cannot be promised — it has to be tested on your own examples.
Where can I download SERA (Ai2 Open Coding Agents) and what does it cost?
The SERA (Ai2 Open Coding Agents) weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.
How I deploy it for clients
- SelectionI pick the model size for your task and hardware and test it on your examples.
- DeploymentI deploy it on your server or in a closed network and provide an API.
- Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
- IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.
Similar models
Mistral models for agentic development: they read the repository, edit files and run commands on their own. The 24B version fits on a single GPU.
DetailsCodeQwen CoderAlibaba (Qwen team) · ChinaCommercial use allowedThe broadest open coding family: from 0.5B for autocompletion to 480B for agents. Qwen3-Coder-Next (80B, 3B active) works as a developer agent on a single GPU.
DetailsTextOLMoAllen Institute for AI (Ai2) · USACommercial use allowedFully open models: not only the weights but also the data, training code and intermediate checkpoints are published. Useful when transparent provenance matters.
DetailsSource: huggingface.co/allenai/SERA-14B. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.


