智能体框架A lightweight, powerful framework for multi-agent workflows
Python · active 2025-03-11 → 2026-08-10 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 518 days from 2025-03-11 to 2026-08-10. Pushes: 2,574 total, peak 69 in a day. Pull requests: 1,774 total, peak 24 in a day. Issues: 1,363 total, peak 26 in a day. Comments: 3,625 total, peak 60 in a day. Stars: 9,665 total, peak 930 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 |
|---|---|---|---|---|
| seratch | 2.9K | 835 | 540 | 812 |
| github-actions[bot] | 2.5K | 1.3K | 416 | 590 |
| rm-openai | 976 | 346 | 203 | 224 |
| chatgpt-codex-connector[bot] | 431 | 0 | 0 | 265 |
| ihower | 96 | 0 | 12 | 76 |
| habema | 90 | 0 | 22 | 39 |
| pakrym-oai | 76 | 18 | 9 | 17 |
| gn00295120 | 63 | 0 | 15 | 37 |
| sibblegp | 62 | 0 | 0 | 54 |
| mshsheikh | 49 | 0 | 35 | 10 |
| Copilot | 45 | 0 | 0 | 17 |
| jhills20 | 36 | 14 | 7 | 2 |
| knowsuchagency | 36 | 0 | 4 | 22 |
| OiPunk | 35 | 0 | 13 | 21 |
| elainegan-openai | 27 | 10 | 1 | 12 |
| Aphroq | 22 | 0 | 11 | 4 |
| akhilsmokie | 22 | 0 | 0 | 0 |
| DanieleMorotti | 21 | 0 | 0 | 17 |
| Ai80-8 | 21 | 0 | 0 | 21 |
| MuhammadHamidRaza | 20 | 0 | 9 | 8 |
Recent activity
Latest issues, pull requests and releases
- Pull request#4298seratch2026-08-08 02:21
- Issue comment#4281abhay-codes072026-08-07 18:58fix: count a model request when the provider omits usage
- Pull request#4287hsusul2026-08-07 18:07
- Issue comment#4161seratch2026-08-05 01:26fix(realtime): release the websocket when the initial session config fails
- Pull request#4126seratch2026-08-02 23:17
- Pull request#3885seratch2026-07-19 23:48
- Issue comment#3837seratch2026-07-15 22:18Question: How should per-invocation Usage be tested with FakeModel?
- Issue#3808HUAN2022A2026-07-11 18:01OpenAIProvider skips conflicting client argument validation under python -O
- Pull request#3730seratch2026-07-04 01:43
- Issue comment#3500github-actions[bot]2026-07-02 02:16feat: add Sailbox sandbox provider
- Issue comment#3708seratch2026-06-30 22:41uv sync fails to resolve with exclude-newer for packages missing upload-time on the simple index (e.g. dockerfile-parse)
- Issue#1912seratch2026-06-30 22:34Python Realtime Voice Agent doesn’t handle output guardrails like Node.js SDK
- Issue#3709seratch2026-06-30 22:32Structured output (`output_type`) is enforced on every turn via `response_format`, suppressing tool calls on strict OpenAI-compatible servers
- Issue comment#3616github-actions[bot]2026-06-26 02:16feat: add Islo sandbox provider
- Issue comment#3566github-actions[bot]2026-06-24 02:16Bind restored handoffs to target agent identity
- Issue comment#3623seratch2026-06-23 23:24Filter code interpreter calls from nested handoff input
- Issue comment#3679seratch2026-06-23 23:23fix: #985 Code Interpreter reasoning replay
- Issue comment#3615github-actions[bot]2026-06-22 02:16fix(daytona): avoid leaking internal hydrate temp path in type error
- Pull request#3488seratch2026-06-19 06:19
- Issue comment#3564github-actions[bot]2026-06-15 02:16fix: cancel in-flight model task when a parallel input guardrail errors
- Issue comment#3573github-actions[bot]2026-06-15 02:16feat: emit agent spans in RealtimeSession for SDK tracing
- Pull request#3604seratch2026-06-09 23:12
- Issue comment#3506github-actions[bot]2026-06-09 02:16feat: Add buffered Chat Completions tool-call streaming
- Issue comment#3514github-actions[bot]2026-06-08 02:16fix(session): strip reasoning item ids from session history
- Issue#3594Pjrich13132026-06-07 03:25Local 300 turn too 500 and homebrew
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 9,665 stars here means stars gained during the window, not the repo's star count.