Automatic LLM router — 82% cost savings, 79.4% accuracy, 93.4% pass rate. Drop-in OpenAI proxy.
active 2026-03-13 → 2026-06-26 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 106 days from 2026-03-13 to 2026-06-26. Pushes: 37 total, peak 4 in a day. Pull requests: 2 total, peak 1 in a day. Issues: 15 total, peak 8 in a day. Comments: 5 total, peak 3 in a day. Stars: 95 total, peak 8 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| anjieyang | 36 | 23 | 0 | 4 |
| Vivien202 | 9 | 7 | 0 | 0 |
| PJSSABER | 3 | 3 | 0 | 0 |
| FantWu2024 | 3 | 2 | 1 | 0 |
| iamagenius00 | 2 | 0 | 0 | 0 |
| not-anjieyang | 2 | 2 | 0 | 0 |
| cjtree04 | 1 | 0 | 0 | 0 |
| wanikua | 1 | 0 | 1 | 0 |
| Duplicated | 1 | 0 | 0 | 1 |
| pupwld5-star | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#11Duplicated2026-05-11 17:28BYOK Providers to inject more models into the routing pool
- Releaseanjieyang2026-05-07 07:09v0.7.18
- Pull request#26FantWu20242026-04-28 04:10
- Issue#24pupwld5-star2026-04-26 21:17Multi-turn conversations fail with `Invalid signature in thinking block` when auto mode switches models
- Issue#16anjieyang2026-04-23 18:34Feedback prior_n=20 is calibrated for multi-user fleet, ineffective for single-user local deployment
- Issue comment#16anjieyang2026-04-23 18:34Feedback prior_n=20 is calibrated for multi-user fleet, ineffective for single-user local deployment
- Issue#5anjieyang2026-04-23 17:40502 error when system http_proxy is set — fix: add NO_PROXY=localhost,127.0.0.1
- Issue#5anjieyang2026-04-23 17:40502 error when system http_proxy is set — fix: add NO_PROXY=localhost,127.0.0.1
- Issue#5anjieyang2026-04-23 17:40502 error when system http_proxy is set — fix: add NO_PROXY=localhost,127.0.0.1
- Issue#20anjieyang2026-04-23 17:28Multi-turn conversations fail with `Invalid signature in thinking block` when auto mode switches models
- Issue#20Vivien2022026-04-23 04:18Multi-turn conversations fail with `Invalid signature in thinking block` when auto mode switches models
- Issue#19iamagenius002026-04-23 04:18Multi-turn conversations fail with `Invalid signature in thinking block` when auto mode switches models
- Issue#19iamagenius002026-04-23 04:17Multi-turn conversations fail with `Invalid signature in thinking block` when auto mode switches models
- Issue#10anjieyang2026-04-02 17:18引入 autosde 维护项目
- Issue comment#10anjieyang2026-04-02 17:17引入 autosde 维护项目
- Issue#10anjieyang2026-04-02 16:31引入 autosde 维护项目
- Issue comment#10anjieyang2026-04-02 16:26引入 autosde 维护项目
- Issue#10anjieyang2026-04-02 16:26引入 autosde 维护项目
- Issue#10anjieyang2026-04-02 16:25引入 autosde 维护项目
- Issue comment#10anjieyang2026-04-02 16:25引入 autosde 维护项目
- Pull request#9wanikua2026-04-02 06:24
- Issue#5cjtree042026-03-27 06:51502 error when system http_proxy is set — fix: add NO_PROXY=localhost,127.0.0.1
- Issue#2Vivien2022026-03-18 07:56select_from_pool() ignores hard_pin=True in tier config, returns wrong model
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 95 stars here means stars gained during the window, not the repo's star count.