The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). It provides a simple yet robust interface using llama.cpp, allowing users to chat with LLM models, execute structured function calls and get structured output. Also supports llama-index and OpenAI Tools.
active 2023-12-29 → 2026-09-24 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 1001 days from 2023-12-29 to 2026-09-24. Pushes: 403 total, peak 21 in a day. Pull requests: 63 total, peak 7 in a day. Issues: 75 total, peak 7 in a day. Comments: 167 total, peak 15 in a day. Stars: 578 total, peak 45 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| Maximilian-Winter | 533 | 394 | 27 | 86 |
| pabl-o-ce | 34 | 1 | 13 | 17 |
| woheller69 | 33 | 0 | 2 | 27 |
| rhohndorf | 16 | 0 | 7 | 6 |
| renovate[bot] | 14 | 8 | 4 | 0 |
| svjack | 11 | 0 | 2 | 2 |
| ibehnam | 10 | 0 | 0 | 5 |
| ebarrragn | 9 | 0 | 0 | 6 |
| robertgro | 3 | 0 | 0 | 1 |
| this-josh | 3 | 0 | 0 | 2 |
| Dakantz | 3 | 0 | 2 | 1 |
| gitrodg1 | 3 | 0 | 0 | 1 |
| rpdrewes | 2 | 0 | 0 | 1 |
| julian-passebecq | 2 | 0 | 0 | 2 |
| erlebach | 2 | 0 | 0 | 0 |
| fahdmirza | 2 | 0 | 0 | 1 |
| jkawamoto | 2 | 0 | 2 | 0 |
| John6666cat | 2 | 0 | 1 | 0 |
| Tuxinet | 2 | 0 | 1 | 0 |
| umiyuki | 2 | 0 | 0 | 2 |
Recent activity
Latest issues, pull requests and releases
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 578 stars here means stars gained during the window, not the repo's star count.