cactus-compute/needle
14MB foundation model for tiny devices; phones, wearables, smart home, and robots.
Doing simple retrieval from LLM models at various context lengths to measure accuracy
Appears on
Quick read
Latest capture 2026-09-05 10:54
0 paths
Agent instructions and tool configuration found in this repository.
No config files detected.
1 observed capture since 2026-09-05. Observed captures are shown by default.
Stars from first capture 0
Observed captures only
All tracked data
Observed snapshots
Observed snapshots
Nearest indexed repositories by embedding similarity.
14MB foundation model for tiny devices; phones, wearables, smart home, and robots.
The simplest, fastest repository for training/finetuning medium-sized GPTs.
a recursive self-improving harness designed to help your agents (and future iterations of those agents) succeed on any task
Anti-laziness skill for AI agents. Core: the Depth Tree method, which splits a task N layers deep and gives every leaf the full time budget of the whole task, so effort multiplies with depth. Grounded in 2025-2026 research on model laziness, underthinking and premature completion.
The best ChatGPT that $100 can buy.
ContextGem: Effortless LLM extraction from documents