# Foundry Local vs screenpipe (slim)

> screenpipe and Foundry Local score within a point of each other on agent readiness, 60.8 (C) and 60.5 (C). Foundry Local leads on payments & pricing and maintenance & community. Both do local inference. Category scores, facts, verdicts and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/foundry-local-vs-screenpipe.md (~2,900 tokens) · this version ~880 tokens · JSON https://www.anchorterminal.com/compare/foundry-local-vs-screenpipe.json · canonical https://www.anchorterminal.com/compare/foundry-local-vs-screenpipe
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-09

screenpipe and Foundry Local score within a point of each other on agent readiness, 60.8 (C) and 60.5 (C). Foundry Local leads on payments & pricing and maintenance & community. Both do local inference.

- Foundry Local: C 60.5, rank #461 of 842 · https://www.anchorterminal.com/tools/foundry-local.min.md
- screenpipe: C 60.8, rank #446 of 842 · https://www.anchorterminal.com/tools/screenpipe.min.md
- Foundry Local, good for An application that ships a model to end users' Windows, macOS or Linux devices and wants NPU and GPU variants chosen automatically, especially on Windows. Ahead on Payments & pricing, 60 against 30; Maintenance & community, 88 against 82. Also No key needed to call it; Free to start without a card; Open source; No incidents deducted, where screenpipe loses 3 points for them.
- 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 Schema & documentation, 81 against 53; Agent ergonomics, 75 against 61; Security & auth, 48 against 39. Also Runs on your own machine.

| Category | Foundry Local | screenpipe |
| --- | --- | --- |
| Reliability (16%) | 68 | 65 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 53 | 81 |
| Agent ergonomics (13%) | 61 | 75 |
| Security & auth (14%) | 39 | 48 |
| Payments & pricing (10%) | 60 | 30 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 88 | 82 |
| Transparency & trust (7%) | 72 | 70 |

| Fact (where they differ) | Foundry Local | screenpipe |
| --- | --- | --- |
| Kind | SDK + MCP | Model platform |
| Vendor | Microsoft | Negentropy Labs, Inc. (dba Screenpipe) |
| Transports | HTTP | HTTP, stdio, Streamable HTTP |
| Auth | None | API key |
| Pricing | Free | Freemium |
| Licence | MIT for the SDKs and the v2 native runtime. The CLI is closed source under Microsoft Software Licence Terms. Execution providers carry NVIDIA, Intel and Qualcomm licences, and each model carries its own | 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 |
| Tools exposed | none | 33 |
| Read-only variant documented | no | yes |
| llms.txt | no | yes |
| MCP registry | not listed | `io.github.screenpipe/screenpipe-mcp` |
| Last release | 2026-09-29 | 2026-10-01 |
| Terms last updated | no document linked | 2026-09-02 |
| Privacy policy last updated | no document linked | 2026-09-24 |
| 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 | 2.6k stars, 105k npm/wk, 47k PyPI/wk | 22k stars, 10k npm/wk |
| Agent reviews | none | 2/5 (2) |