rec
rec is Recursive’s custom inference engine for running its language models locally on a machine. It provides a local API compatible with OpenAI and Anthropic chat-completion formats and supports single-session usage.
What it does
Developers can use rec to run Recursive language models locally and connect them to supported harnesses or their own API clients.
- Availability
- Install using the provided shell command
- Pricing model
- Not established
- Deployment
- Runs locally on an Apple Silicon Mac
- Privacy
- Not established
- Licence
- Apache 2.0
Capability
Modality
Access
Deployment
Pricing
Target user
Evidence
6 claims- rec is a custom inference engine for running Recursive language models locally. [1]
`rec` is our custom inference engine for running [Recursive's language
GitHub new repositories. Quoted text is outside CC BY 4.0 and keeps its original rights. - rec exposes OpenAI- and Anthropic-compatible chat-completion APIs. [1]
`rec` exposes OpenAI and Anthropic-compatible chat-completion APIs.
GitHub new repositories. Quoted text is outside CC BY 4.0 and keeps its original rights. - The README provides a shell command to install rec. [1]
- rec requires an Apple Silicon Mac with an M4 Pro, M4 Max, M5 Pro, or M5 Max and at least 48 GB unified memory. [1]
- Apple Silicon Mac with an M4 Pro, M4 Max, M5 Pro, or M5 Max
GitHub new repositories. Quoted text is outside CC BY 4.0 and keeps its original rights. - rec is optimized for single-session usage. [1]
⚠️ rec is optimized for single-session usage.
GitHub new repositories. Quoted text is outside CC BY 4.0 and keeps its original rights. - The repository lists its licence as Apache 2.0. [1]
Sources
1
1
GitHub new repositoriesOwner-controlled
https://github.com/recursive-oss/rec
Retrieved 2026-10-29 00:58 UTC
Verified
Versions
2| Version | Effective | Change | Changed fields | State |
|---|---|---|---|---|
| 2 | 2026-10-27 00:42 UTC | material change | pricing, availability, deployment | Current |
| 1 | 2026-10-26 00:03 UTC | publication | None | Current |
In briefs
1- A speech model adds multilingual transcription and translation Daily brief 2026-10-26
Original catalog content is licensed under CC BY 4.0, attributed to wowsuchai. Source quotations and linked content keep their original rights.
