Compare frameworks
Haystack vs Letta vs AutoGen
Every figure below carries the source that reported it and the moment it was observed. Values that failed validation are withheld rather than shown, and a dash means no source we track carries that field for that framework.
| Field | Haystack | Letta | AutoGen |
|---|---|---|---|
| Stars | 26,584Synced from sourceCurrent3h ago | 24,864Synced from sourceCurrent3h ago | 61,130 (highest of the compared values)Synced from sourceCurrent3h ago |
| downloads | — | — | 47,487Synced from sourceAging6d ago |
| Last commit | 2026-09-23Synced from sourceCurrent3h ago | 2026-09-10Synced from sourceCurrent3h ago | 2026-04-15Synced from sourceCurrent3h ago |
| Language | pythonSeeded, unreviewedwritten 1mo ago | pythonSeeded, unreviewedwritten 1mo ago | pythonSeeded, unreviewedwritten 1mo ago |
| Licence | Apache-2.0Synced from sourceCurrent3h ago | Apache-2.0Synced from sourceCurrent3h ago | CC-BY-4.0Synced from sourceCurrent3h ago |
| Archived | noSynced from sourceCurrent3h ago | noSynced from sourceCurrent3h ago | noSynced from sourceCurrent3h ago |
| Category | ragSeeded, unreviewedwritten 1mo ago | memorySeeded, unreviewedwritten 1mo ago | multi-agentSeeded, unreviewedwritten 1mo ago |
| Contributors | 475Synced from sourceCurrent3h ago | 155Synced from sourceCurrent3h ago | 534Synced from sourceCurrent3h ago |
| Forks | 3176Synced from sourceCurrent3h ago | 2628Synced from sourceCurrent3h ago | 9246Synced from sourceCurrent3h ago |
| Maintainer | deepsetSeeded, unreviewedwritten 1mo ago | LettaSeeded, unreviewedwritten 1mo ago | MicrosoftSeeded, unreviewedwritten 1mo ago |
| Open issues | 168Synced from sourceCurrent3h ago | 0Synced from sourceCurrent3h ago | 1098Synced from sourceCurrent3h ago |
| PyPI downloads, monthly | — | — | 263297Synced from sourceAging6d ago |
| PyPI downloads, weekly | — | — | 47487Synced from sourceAging6d ago |
| PyPI package | haystack-aiSynced from sourceCurrent3h ago | lettaSynced from sourceCurrent3h ago | pyautogenSynced from sourceCurrent3h ago |
| PyPI released | 2026-09-03T09:27:43.312258ZSynced from sourceCurrent3h ago | 2026-09-23T23:59:05.225455ZSynced from sourceCurrent3h ago | 2025-07-15T00:37:26.170442ZSynced from sourceCurrent3h ago |
| Requires Python | >=3.10Synced from sourceCurrent3h ago | >=3.9Synced from sourceCurrent3h ago | >=3.10Synced from sourceCurrent3h ago |
| PyPI version | 3.1.1Synced from sourceCurrent3h ago | 0.33.0Synced from sourceCurrent3h ago | 0.10.0Synced from sourceCurrent3h ago |
| Repository | https://github.com/deepset-ai/haystackSynced from sourceCurrent3h ago | https://github.com/letta-ai/lettaSynced from sourceCurrent3h ago | https://github.com/microsoft/autogenSynced from sourceCurrent3h ago |
Sources: GitHub REST API, npm registry downloads, PyPI registry metadata, pypistats.org downloads. Most recent observation 3h ago. Where a row is marked, ▲ is the highest of the values shown and ▼ the lowest — arithmetic on the figures above, not a ranking or a recommendation. Rows where neither extreme is meaningful are left unmarked rather than given a direction they do not have.
Change the comparison
Remove one, or open the directory to pick a different set. Up to 3 at a time.