PyPI Stats
  • Insights
  • PyPI
  • GitHub
  • Search
  • Compare
  • Advisories
  • Ecosystem
  • About
Home

Search Packages

Find Python packages by name, description, GitHub topic, or filter by metrics
cuga-project
cuga

CUGA is an open-source generalist agent harness for the enterprise, supporting complex task execution on web and APIs, OpenAPI/MCP integrations, composable architecture, reasoning modes, and policy-aware features.

450K 713 126
vstorm-co
pydantic-ai-backend

File Storage & Sandbox Backends for Pydantic AI: console tools for file operations, Docker-isolated sandboxes for safe execution, and permission system with presets for access control. Enables secure multi-user handling and testing in agents via in-memory, local, or containerized storage.

191K 86 19
yaroslaff
evalidate

Safe and fast evaluation of untrusted user-supplied python expressions

47K 40 4
alibaba
opensandbox

Secure, Fast, and Extensible Sandbox runtime for AI agents.

46K 10K 827
agentbay-ai
wuying-agentbay-sdk

The Cloud Sandbox Built for AI Agents

36K 1K 50
boxlite-ai
boxlite

Sandboxes for every agent. Embeddable, stateful, snapshots, and hardware isolation.

18K 2K 108
alibaba
opensandbox-server

Secure, Fast, and Extensible Sandbox runtime for AI agents.

16K 10K 827
shroominic
codeboxapi

👾📦 CodeBoxAPI is the simplest sandboxing infrastructure for your LLM Apps and Services.

15K 364 44
alibaba
opensandbox-code-interpreter

Secure, Fast, and Extensible Sandbox runtime for AI agents.

13K 10K 827
CelestoAI
smolvm-core

Open-source AI sandbox infrastructure for code execution, browser use, and AI agents.

11K 492 32
capsulerun
capsule-run

Secure runtime to sandbox AI agent tasks. Run untrusted code in isolated WebAssembly environments.

10K 281 18
superradcompany
microsandbox

🧱 secure, local and programmable sandboxes for AI agents

10K 6K 289
EXboys
skilllite

A lightweight secure Self-evolution engine built in Rust, featuring a built-in native system-level sandbox, zero dependencies, and fully local execution.

7K 118 13
sattyamjjain
agent-airlock

Open-source security firewall for AI agents — validates tool calls, strips ghost arguments, enforces type safety, PII masking, RBAC, cost tracking & sandbox isolation. Works with LangChain, OpenAI Agents SDK, PydanticAI & CrewAI.

7K 6 0
ClawWorksCo
lasso-sandbox

Run AI coding agents (Claude Code, OpenCode) safely inside sandboxed Docker containers with audit logging

7K 0 0
Unifield
ufload

Unifield Loader

6K 1 2
KroMiose
nekro-agent

NekroAgent 是一个面向多人互动场景的跨平台 Agent 框架,集 Claude Code 沙盒执行、工作区编排、长期记忆、结构化 MCP 管理与可视化控制台于一体,兼具高扩展性、多模态交互、实时状态推送和自动化运行能力。项目支持 QQ、Discord、Telegram、Minecraft、BilibiliLive、WeChat、Email、SSE(SDK) 等多种平台接入,应用于构建高智能聊天机器人,可扩展为具备代码执行、工具调用、插件协作和复杂任务处理能力的通用 Agent 系统

6K 825 69
ashenfad
agex

Library-friendly Agents

6K 43 5
vmehera123
leashd

Safety-first agentic coding framework. Three-layer safety pipeline (sandbox, YAML policies, human-in-the-loop approval) for AI coding agents. Pluggable runtimes (Claude Code, Codex), autonomous task orchestrator, full audit trail.

6K 3 0
HACKE-RC
bandsox

Sanboxes for AI agents and humans

5K 71 4
TheUncharted
zapcode

TypeScript interpreter for AI agents. Written in Rust. 2µs cold start. Sandboxed. Alternative to MCP tool calling.

5K 75 2
NevaMind-AI
memu-py

Memory for 24/7 proactive agents like OpenClaw.

4K 14K 1K
bytecodealliance
wasmtime-bin

A lightweight WebAssembly runtime that is fast, secure, and standards-compliant

4K 18K 2K
FloHofstetter
shoreguard

Open source control plane for NVIDIA OpenShell

4K 3 1
    • Data from PyPI, GitHub, ClickHouse, and BigQuery