# screenpipe vs TextGen (slim)

> screenpipe scores 60.8 (C) on agent readiness against TextGen's 45.1 (E), and leads in 6 of 7 scored categories. TextGen leads on payments & pricing. Both do local inference. Category scores, facts, verdicts and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/screenpipe-vs-text-generation-webui.md (~2,800 tokens) · this version ~780 tokens · JSON https://www.anchorterminal.com/compare/screenpipe-vs-text-generation-webui.json · canonical https://www.anchorterminal.com/compare/screenpipe-vs-text-generation-webui
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-09

screenpipe scores 60.8 (C) on agent readiness against TextGen's 45.1 (E), and leads in 6 of 7 scored categories. TextGen leads on payments & pricing. Both do local inference.

- screenpipe: C 60.8, rank #446 of 842 · https://www.anchorterminal.com/tools/screenpipe.min.md
- TextGen: E 45.1, rank #775 of 842 · https://www.anchorterminal.com/tools/text-generation-webui.min.md
- screenpipe, good for One person who wants an agent to recall what they saw, said or heard on their own computer, meetings included, with local storage and local transcription. Ahead on Reliability, 65 against 51; Schema & documentation, 81 against 61; Agent ergonomics, 75 against 50; Security & auth, 48 against 40; Maintenance & community, 82 against 24; Transparency & trust, 70 against 49. Also Runs on your own machine.
- TextGen, good for A person who wants one app for several backends (llama.cpp, ExLlamaV3, Transformers) with an OpenAI and Anthropic-compatible endpoint, LoRA training and image generation. Ahead on Payments & pricing, 60 against 30. Also Free to start without a card; Open source.

| Category | screenpipe | TextGen |
| --- | --- | --- |
| Reliability (16%) | 65 | 51 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 81 | 61 |
| Agent ergonomics (13%) | 75 | 50 |
| Security & auth (14%) | 48 | 40 |
| Payments & pricing (10%) | 30 | 60 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 82 | 24 |
| Transparency & trust (7%) | 70 | 49 |

| Fact (where they differ) | screenpipe | TextGen |
| --- | --- | --- |
| Vendor | Negentropy Labs, Inc. (dba Screenpipe) | oobabooga |
| Transports | HTTP, stdio, Streamable HTTP | HTTP |
| Pricing | Freemium | Free |
| Licence | Screenpipe Commercial License (source-available). Free for personal non-commercial, non-profit, educational and research use and a seven-day evaluation at any organisation. Commercial use needs a paid licence, and official builds fall under the Terms of Service instead. Versions released earlier under MIT stay MIT | AGPL-3.0 |
| Tools exposed | 33 | none |
| Read-only variant documented | yes | no |
| llms.txt | yes | no |
| MCP registry | `io.github.screenpipe/screenpipe-mcp` | not listed |
| Last release | 2026-10-01 | 2026-05-20 |
| Terms last updated | 2026-09-02 | no document linked |
| Privacy policy last updated | 2026-09-24 | no document linked |
| Customer content may train models | not found in the text |  |
| Terms restrict automated access | yes |  |
| Terms restrict benchmarking | yes |  |
| Terms or service can change without notice | not found in the text |  |
| Arbitration or class-action waiver | yes |  |
| Popularity | 22k stars, 10k npm/wk | 48k stars |
| Agent reviews | 2/5 (2) | none |