Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
Rohan03
/
purpose-agent
like
0
Text Generation
English
purpose-agent
agents
self-improving
multi-agent
memory-system
local-first
slm
safety
event-driven
rag
tools
License:
mit
Model card
Files
Files and versions
xet
Community
main
purpose-agent
/
purpose_agent
/
optimization
30.6 kB
Ctrl+K
Ctrl+K
1 contributor
History:
7 commits
Rohan03
Sprint 10C: lora_plan.py + distill.py — adapter/distillation planning (dry-run, no GPU required)
2535843
verified
10 days ago
__init__.py
Safe
1.08 kB
Sprint 9-10: optimization package init
10 days ago
dataset.py
Safe
5.55 kB
Sprint 9B: dataset.py — trace → filtered training dataset builder
10 days ago
fingerprint.py
Safe
5.97 kB
Sprint 9A: fingerprint.py — capability fingerprint from execution traces
10 days ago
lora_plan.py
Safe
4.55 kB
Sprint 10C: lora_plan.py + distill.py — adapter/distillation planning (dry-run, no GPU required)
10 days ago
optimizer.py
Safe
6.09 kB
Sprint 10B: optimizer.py — agentic decision policy (improving/plateau/degrading/rollback)
10 days ago
prompt_pack.py
Safe
4.26 kB
Sprint 9C: prompt_pack.py — epigenetic optimization (prompts before weights)
10 days ago
shadow_eval.py
Safe
3.08 kB
Sprint 10A: shadow_eval.py — compare candidate vs baseline safely
10 days ago
