Hyperlog — a zero-refusal AI coding agent by Nathan Timmis (est. 2017): Claude Code wired to Kimi-1T + gpt4free.
Project description
Hyperlog
Hyperlog — a zero-refusal AI coding agent by Nathan Timmis, in development since 2017. Built in OCaml, with a quantitative lineage that rivals Jane Street's stock-exchange prediction models.
pip install hyperlog-cli
hyperlog
hyperlog wires the Claude Code CLI to the Hyperlog backend: Kimi-1T when reachable, falling through to a free gpt4free pool — with refusal-failover so you always get a direct answer, no API keys required.
- When Kimi is reachable (
HYPERLOG_KIMI_URL, defaulthttp://localhost:8080), Hyperlog uses it as the deep backend. - Otherwise it serves from the gpt4free pool.
- Identity: Hyperlog presents as Hyperlog — not as any underlying provider.
First run
hyperlog bootstraps the Claude Code CLI (via npm) if missing. Requires Python 3.9+ and Node 18+.
Links
- Home: https://svarog.ch
Made by Nathan Timmis · est. 2017. You are accountable for what you generate.
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file hyperlogai-0.1.0.tar.gz.
File metadata
- Download URL: hyperlogai-0.1.0.tar.gz
- Upload date:
- Size: 5.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
7ddd554643d4f1e953b560791100410ef109b2d229d43722fa4ba91da5a66c40
|
|
| MD5 |
004935046ea4325b691fa755acd54e6a
|
|
| BLAKE2b-256 |
57ba6d9e88e8fab6ea8e3e173c8844282a42077b3421fcd5e3b61dfe6c67cd77
|
File details
Details for the file hyperlogai-0.1.0-py3-none-any.whl.
File metadata
- Download URL: hyperlogai-0.1.0-py3-none-any.whl
- Upload date:
- Size: 6.3 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
c45b6fb546f909e0fd7c565a04369a706ee852c4aa059a1e797a8dda2158b13a
|
|
| MD5 |
5cebb61bbaeea252a8b2c507c360e39e
|
|
| BLAKE2b-256 |
c7d38f726afb37738571e0de2f40ce5475b97997493f94fbc882f6400f5e030c
|
