vllm-project/agentic-api
Stateful API logic for agentic applications using vLLM
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
5 releases in the last 90 days, the latest 36 days ago, with 29 contributors on GitHub.
Use Cases & Benefits
- Provides a Rust-native, stateful API layer for agentic applications that manages conversation state, tool execution, and multi-turn orchestration on the server side.
- Eliminates client-side complexity by handling state hydration, tool calls, and streaming in a single OpenAI-compatible Responses API call.
- Use for deploying OpenAI-compatible agentic workloads on your own GPUs with vLLM as the inference backend.
- Use for running Codex or Claude Code sessions locally with full WebSocket and tool integration without requiring an OpenAI account.
- Use for building server-side applications that require multi-step tool chains and background execution with explicit tool ownership and concurrency control.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
Apache 2.0
Permissive: commercial use, modification and redistribution are allowed with attribution; includes an explicit patent grant from contributors.
Community files
- README: present
- Contributing guide: present
- Code of conduct: present
Watch-outs
No watch-outs from GStars' checks.
General guidance from repository metadata, not legal advice. How we score
From the README
The stateful, agentic API layer for vLLM, written in Rust 🦀
Run OpenAI-grade agentic workloads (Responses API, server-side tools, Codex) on your own GPUs.
vLLM gives you state-of-the-art inference throughput. But real agentic applications need more than raw tokens: they need conversation state, tool-call loops, and multi-turn orchestration. Today, all of that complexity lives in your client code.
Agentic API moves it server-side. It is a Rust-native gateway that sits in front of vLLM and owns the stateful agentic APIs, starting with an OpenAI-compatible Responses API. vLLM is one supported backend, not part of the Agentic API product name. Your application makes one API call and the server handles the rest: state hydration, tool execution, streaming, and continuation.
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
+127 stars over 60 days across 7 snapshot days; best day +16 on Sep 8.
Forks
100+42
Open issues
87+19
Compared with peers in API
Fastest-growing repositories GStars tracks in this cohort for the week of Nov 1, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| vxcontrol/pentagi | 33.5K | +712 | 38 | 31 days ago |
| usebruno/bruno | 48.2K | +281 | 59 | 14 days ago |
| agentgateway/agentgateway | 6.0K | +183 | 60 | 9 days ago |
| mudler/LocalAI | 50.2K | +176 | 59 | 12 days ago |
| sveltejs/svelte | 88.6K | +77 | 65 | 9 days ago |
| vllm-project/agentic-api | 340 | — | 58 | 36 days ago |
| Category median | 48.2K | +183 | 59 | — |
Also by vllm-project
Other repositories from this maintainer that GStars tracks
- Python95.9K stars
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
- Python7.4K stars
vllm-omni
A framework for efficient model inference with omni-modality models
- Go6.3K stars
semantic-router
An open, programmable decision layer for models and compute.
- Go5.2K stars
aibrix
Cost-efficient and pluggable Infrastructure components for GenAI inference
- Python3.0K stars
vllm-ascend
Community maintained hardware plugin for vLLM on Huawei Ascend
Discover Repositories
Search across tracked repositories by name or description