Skip to content
The Daily Repo

AuremHQ / weight-space-programming

wsp-kit by Aurem — an engineering tool for small models. Try to fix small open-weight models by editing weights directly, no retraining. An eval gate decides.

Why this job: works in the areas we cover, but does not say which job it does

wsp-kit — real runs

What it does

We ran the kit on real models — Qwen3-0.6B, GPT2-124M, and SmolLM2-1.7B-Instruct, local CPU, no LLM editor. 7 real runs, 2 gate passes. Here is what actually happened. Full numbers: REAL-RUNS.md.

Get started

No single install command. Read the steps in the README (opens in new tab)

Maintenance
Active
Last commit 5 days ago
Stars
16
+8 this week
Licence
MIT
Allows business use
Downloads for
None listed
No release files
Latest version
None yet
No releases
Built with
Python
97% of the code

Is it looked after?

Contributors
1
Last 90 days
Issues
None
No issues filed
Pull requests
0 merged
0 waiting
Releases
None
Never published
  • No contributing guide
  • No security policy
  • No code of conduct

Similar repos

Repos similar to this one
RepoStarsLast commitLicenceDownloads for
chrishayuk / larql1,175todayApache-2.0Mac, Windows, Linux
Extraltodeus / J-Wash2422 months agoApache-2.0No downloads
ninjahawk / Subtext2483 months agoCustomNo downloads
More: languages, topics and project record

Languages

  • Python 97%
  • Shell 3%

Topics

  • ai-engineering
  • eval-gate
  • llm
  • machine-learning
  • mcp
  • open-source
  • python
  • weight-space-programming
  • mechanistic-interpretability
  • open-weight-models
  • model-editing
  • small-language-models

Project record

  • JobOther AI tools
  • StatusNew to our list
  • Commits86
  • Forks2
  • Watching0
  • CreatedNov 4, 2026
  • First seen by usNov 7, 2026
  • CheckedNov 12, 2026

Type to search.

Try