Sign in
← Back to search
github Not archived

gkamradt/needle-in-a-haystack

Doing simple retrieval from LLM models at various context lengths to measure accuracy

1 awesome list

Quick read

Stars
2,397
Forks
245
Open issues
29
Commits
90

Activity and growth

Latest capture 2026-10-17 03:16

Stars · last 7 days
0 0.0%
Commits · last 7 days
0 0.0%
Stars since tracking
+17
Stored snapshots
2

Classification

Technology stack

pytest

Metadata

Language
Jupyter Notebook
License
NOASSERTION
Default branch
main
Created
2023-11-11
First commit
2023-11-11
Last pushed
2026-06-08
GitHub updated
2026-10-15
Last synced
2026-10-17 03:16
Stack scanned
2026-10-17 03:16
Archived
No

Archive status reflects the last catalog sync, not a maintenance assessment. Check recent releases, issue responses, and fit for your project with the repository shortlisting checklist.

Sign in to like gkamradt/needle-in-a-haystack
README View on GitHub

AI development signals

0 paths

Agent instructions and tool configuration found in this repository.

No config files detected.

Growth history

Tracked growth

2 observed captures since 2026-09-05. Observed captures are shown by default.

Stars from first capture +17

Chart data

Observed captures only

Time horizon

All tracked data

Custom date range

Stars history

Observed snapshots

Commits history

Observed snapshots

Similar repositories

Nearest indexed repositories by embedding similarity.

cactus-compute/needle

Automation foundation model for tiny devices: 2-bit, 8-29 MB, tool calls, ASR, structured extraction and embeddings on phones, wearables, smart homes, robots, cars and microcontrollers.

14,057 stars
Python 2 awesome lists

ninjahawk/livenerf

Benchmark for tracking model capability after release.

1,518 stars
Python 0 awesome lists

karpathy/nanoGPT

The simplest, fastest repository for training/finetuning medium-sized GPTs.

63,456 stars
Python 2 awesome lists

greyhaven-ai/autocontext

a recursive self-improving harness designed to help your agents (and future iterations of those agents) succeed on any task

1,309 stars
Python 1 awesome list

lynote-ai/humanize-text

Open-source text humanization pipeline with every intermediate step published. Two LLM rewrites at temp 1.3, then two hops across different NMT engines. Four documented methodologies you can read, modify, and run locally.

3,048 stars
Python 1 awesome list

Leonxlnx/unlazy

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.

3,139 stars
JavaScript 1 awesome list