Search public pages, research tools, and SAVRN solutions.
SAVRN Model Hub · Models by Task
1 open-weight agent models in the SAVRN Model Hub, with Balogun Saheed publishing the most.
| Model | Publisher | Parameters | License | Monthly downloads | Cheapest GPUs at 16-bit |
|---|---|---|---|---|---|
| mira-agent-instinct | Balogun Saheed | — | apache-2.0 | — | — |
| License | Models | Commercial use |
|---|---|---|
| apache-2.0 | 1 | Yes |
| Publisher | Models |
|---|---|
| Balogun Saheed | 1 |
Mira is an agent-oriented LLM with instinctive reasoning compression and safe recursive self-improvement loops. Designed for long-horizon tasks, tool use, and self-play fine-tuning with eval gating. Results in.evalresults/: Terminal-Bench 2.1 Not AGI. Agent-oriented LLM with heuristic compression. Recursive self-improvement is offline and eval-gated. Tool use requires guardrails. Apache-2.0
By monthly downloads reported by the Hugging Face Hub: .