# GraphBit — Type-Safe Agentic Framework (Rust + Python) > GraphBit is an open-source agentic framework for deterministic, concurrent execution with type safety, guardrails, observability, and multi-LLM support. ## Install Copy the content below into your project: ## Quick Use ```bash pip install graphbit ``` ```python from graphbit import LlmConfig, Executor config = LlmConfig.openai("$OPENAI_API_KEY", "gpt-4o-mini") executor = Executor(config) # See README for full workflow/node example ``` ## Intro GraphBit is an open-source agentic framework focused on deterministic, concurrent execution with guardrails and observability. It provides a `pip install graphbit` quick start, and the repo is GitHub-verified at 537★. **Best for:** building agent workflows that need determinism, concurrency control, and production-grade guardrails **Works with:** Python package + Rust runtime; multi-LLM providers; tool functions with descriptions; workflow graphs **Setup time:** 10–20 minutes ### Key facts (verified) - README includes a benchmark table claiming large CPU/memory multipliers vs other frameworks (as stated in README). - README lists supported Python versions 3.9–3.13 and shows `pip install graphbit`. - README includes a workflow example with tool decorators and node graphs. - GitHub: 537 stars · 115 forks; pushed 2026-04-28 (GitHub API verified). ## Main When evaluating an agent framework, test three things early: - Can you reproduce outputs (determinism) under retries? - Can you cap concurrency and costs under load? - Do guardrails and observability give you enough signal to debug failures? Use GraphBit's quick start to build a small workflow graph and add one real tool call (filesystem/API) before committing to a migration. ### README excerpt (verbatim)
### FAQ
**Q: How do I install GraphBit?**
A: Install with `pip install graphbit` per README.
**Q: What makes it different?**
A: README emphasizes deterministic, concurrent execution plus guardrails and observability.
**Q: Does it support multiple LLMs?**
A: Yes—README lists multiple providers and shows provider configs.
## Source & Thanks
> Source: https://github.com/InfinitiBit/graphbit
> License: Apache-2.0
> GitHub stars: 537 · forks: 115
---
## 快速使用
```bash
pip install graphbit
```
```python
from graphbit import LlmConfig, Executor
config = LlmConfig.openai("$OPENAI_API_KEY", "gpt-4o-mini")
executor = Executor(config)
# 完整 workflow/node 示例见 README
```
## 简介
GraphBit 是开源 agent 框架,强调确定性与并发执行,内置 guardrails 与可观测性。它提供 `pip install graphbit` 快速安装方式,仓库 GitHub 已验证 537★。
**最适合:** 需要确定性、并发控制与生产级 guardrails 的 agent 工作流开发
**适配:** Python 包 + Rust runtime;多 LLM provider;带描述的工具函数;工作流图
**配置时间:** 10–20 分钟
### 关键事实(已验证)
- README 提供 benchmark 表(为 README 自述数据),对比其他框架的 CPU/内存倍数。
- README 标注 Python 3.9–3.13,并给出 `pip install graphbit`。
- README 给出带 tool 装饰器与节点图的工作流示例代码。
- GitHub:537 stars · 115 forks;最近更新 2026-04-28(GitHub API 验证)。
## 正文
评估 agent 框架时,建议尽早验证三件事:
- 重试/失败恢复下是否还能保持可复现(确定性)?
- 在负载下能否限制并发与成本?
- guardrails + 可观测性是否足以定位失败原因?
可以先按 GraphBit 的 quick start 搭一个小 workflow graph,再加一个真实 tool(文件系统或 API)来跑通端到端,再决定是否迁移。
### README 原文节选(verbatim)
### FAQ
**怎么安装 GraphBit?**
答:按 README:`pip install graphbit`。
**它的定位是什么?**
答:README 强调确定性与并发执行,并提供 guardrails 与可观测性。
**支持多 LLM 吗?**
答:支持:README 列出了多个 provider 并展示配置方式。
## 来源与感谢
> Source: https://github.com/InfinitiBit/graphbit
> License: Apache-2.0
> GitHub stars: 537 · forks: 115
---
Source: https://tokrepo.com/en/workflows/graphbit-type-safe-agentic-framework-rust-python
Author: Agent Toolkit