compare
5ire vs llama.cpp
The same facts for both, read from GitHub every night, and the relation a person reviewed.
| Fact | 5ire | llama.cpp |
|---|---|---|
| Language | TypeScript | C++ |
| Licence | Other | MIT |
| Stars | 5.4k | 130k |
| Latest | v0.15.4 | v0.6.0 |
| Last push | 2026-09-14 | 2026-10-06 |
| Release cadence | about 25 days between releases | too few releases |
| Active contributors | 2 commit authors on the default branch in the last 90 days | 173+ commit authors on the default branch in the last 90 days |
| Flags | none | none |
How they relate
Both replace ChatGPT. Alternatives to ChatGPT →
Partial5ireDesktop chat app for hosted and local models, with MCP tools and a local knowledge base.
Partialllama.cppRuns open-weight models on CPU or GPU, with a built-in server and a minimal web chat.
5ire
- v0.15.42026-03-180.15.4
- v0.15.32026-01-20Fixed an issue where overly long MCP server tool names could cause errors.
- v0.15.22025-12-230.15.2
- v0.15.02025-12-02We’ve migrated the storage engine from SQLite + LanceDB to pglite.
- v0.15.12025-12-02Hotfix: Fixed an error that caused knowledge-base file imports to fail.
llama.cpp
- b114452026-10-06vulkan : check for null vkEnumerateInstanceVersion (#29872)pre-release
- b114432026-10-06models : consolidate nextn row cropping into shared helpers (#30017)pre-release
- b114402026-10-06llama : re-reserve the sched when the nextn extraction flags change (#30020)pre-release
- b114392026-10-06ggml: refactor selective expert copying to user code (#29943)pre-release
- b114382026-10-06test-llama-archs : initialize backends before generating models (#30034)pre-release
5ire
unsigned The latest release, v0.15.4, carries no signature GitHub could verify.
Loading the security report
llama.cpp
unsigned The latest release, v0.6.0, carries no signature GitHub could verify.
Loading the security report