Havuz

Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts wit

Claude Code-style declarative permission rules for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), and

Open-Source Agentic Harness for Reliable Task Completion, even on small local models. 💻🧠🤖

Ephemeral Workspaces, durable shared history. LayerFS gives every agent a complete, writable filesystem Workspace over shared committed hist

自托管 AI Coding Agent（Rust）：常驻 Runtime 撑起终端 / 浏览器 / 手机三端；每行改动可追溯到具体 Agent 与工具调用，子 Agent 的活由退出码裁决，检查点回退、目标 token 预算与验收清单跨轮次跨重启累计，用量与反馈账本留在本地。接任

Verify what AI coding agents can actually read, write, execute and reach using synthetic canaries.

Vmware Workstation 17 Pro - Local Windows build featuring every professional module and a simple install routine.

Open-source, self-hosted AI agent for terminal, Telegram and Raspberry Pi. Local Ollama or Claude/Codex workers, enforced by a deterministic

An open-source workspace for coding agents, running on your own machine. More work. Less AI waste. Same subscriptions.

Self-hosted AI gateway with a built-in dashboard. OpenAI-compatible API, multi-tenant, sandboxed code execution, MCP integrations, file stor

Sandboxed multi-scanner security for AI skills, MCP servers, and package trees — coverage honesty, SIE judging, heatmap posture, guided tria

Bounded repository context and verified patches for Codex and Claude Code. Explicit edit grants, source fingerprints, isolated worktrees, ac

Give Pi one typed tool instead of a toolbox.

Self-hosted execution platform for AI agents, powered by gVisor.

Evidence-first infrastructure for reproducible, isolated executable evaluation and online rewards.

epoint.az ödəniş gateway-inin lokal sandbox-u. Bir konteynerdə: API, ödəniş səhifəsi, callback-lər və dashboard.

Rootless container runtime with no daemon. Runs agent tool calls and LLM-generated code in kernel-enforced containers.

MCP server for Claude Desktop and other Model Context Protocol clients — sandboxed filesystem access (read/write/edit/search) plus Dev Mode-

OpenShell Kubernetes Operator

One TypeScript API for running code in sandboxes. Write it once, run it on E2B, Daytona, Vercel Sandbox, Upstash Box, Railway, Tenki, Freest

Agent interoperability and security, out of the box. The network layer underneath A2A: reachable, end-to-end sealed and payable agents witho

Aggregated Kubernetes apiserver and e2b-compatible data plane for warm-pooled agent sandboxes on microVMs. Sandboxes are served from per-nod

Claude Code delegates coding to isolated CLI agents it doesn't trust (Codex, OpenCode, Pi, Pythinker), freezes what they produce, verifies i

在網路受限的 Docker Dev Container 裡安全執行 Claude Code，透過 iptables/ipset 防火牆白名單限制 AI Agent 的對外連線，降低資料外洩與誤操作風險。改自 Anthropic 官方 .devcontainer 參考實作。

Open-source AI app builder — turn a prompt into a full-stack Next.js web app with built-in hosting, sandbox, database, auth, AI integration,

Sandbox for running AI coding agents autonomously: isolated, network-restricted, host-safe

Dormice, AI agents için kalıcı sandbox’ları self-hosted makinelerde çalıştıran ve E2B uyumlu bir sandbox platformudur.

Neden yükseliyor · 81 günde 1283 yıldız ve son 28 günde 115 commit kayda değer ilgi ve geliştirme temposu gösteriyor. Agent sandbox’larını self-hosted ve düşük boşta çalışma maliyetli hale getirme vaadi de güncel bir ihtiyaca karşılık geliyor. Ancak commit’lerin tek yazardan gelmesi nedeniyle bu hareketlilik bağımsız katkı veya benimsenme kanıtı sayılmaz; yükselişin kesin nedeni verilerden anlaşılamıyor.

Your dashboard is data. Any AI can build it; any human can edit it. A protocol + runtime for agent-composable dashboards — layout-as-data, o

炼妖壶 — run Claude Code, Codex, or any coding agent in a deny-default sandbox with VPN-only network egress. sandbox-exec + PF on macOS, Landlo

clawk, coding agents için kod deposunu kullanan ancak ana makineden ayrı, disposable Linux VM ortamları oluşturan bir araçtır.

Neden yükseliyor · Coding agents'a güvenli çalışma alanı sağlama ihtiyacını tek komutla kullanılabilen disposable VM yaklaşımıyla ele alıyor; 83 günde 1.021 yıldız dikkat çekiyor. Ancak son 28 günde commit olmaması, ilginin güncel geliştirme faaliyetiyle desteklendiğini göstermiyor.

A hypervisor and sandbox cloud for self-hosting AI agents and RL

Warm, disposable GitHub Actions runners with Docker Sandboxes microVM isolation across Linux, macOS, and Windows hosts. Designed for teams t

Fast cold-boot MicroVM sandboxes for AI agents on cocoon

Open-source continuation of Daytona — secure, elastic sandbox infrastructure for AI code execution and agent workflows. Community fork of th

Mobile-native agent SDK for building on-device AI agents with sandboxed execution, extensible tools, and x-app / x-agent / x-channel connect

Run Claude Code (or another coding agent) unattended, inside a disposable microVM, with its work committed to git so you can review everythi

Automated WSL2 installer for Claude Science's operon daemon — environment checks, sandbox setup, and one-command startup.

Sandboxed computer-use MCP — drive a real browser + desktop apps in a nested X11 window.

On-demand Linux computers you can hand to an AI — real Firecracker microVMs with a browser, terminal, coding agents, and an AI that drives t

Confine an AI coding agent to one directory with a BPF-LSM program, and watch every escape it tries.

Your agent, across all your machines. A self-hosted, web-based AI agent: one server holds every conversation and works in a cloud sandbox or

Cloud IDE + autonomous AI coding agent - Kubernetes-powered instant dev sandboxes with LangChain ReAct agent that reads, writes & ships mult

Open-source sandboxes for AI agents — run untrusted, AI-generated code safely on your own machine.

Local AI agent sandbox runtime with Firecracker, gVisor, and NVIDIA GPU sandbox support.

CLI for Local Isolated Environments for Coding Agents

extremely fast web remote desktop streaming

eve, dosya ve klasörleri agent yapılandırma arayüzü olarak kullanan TypeScript tabanlı bir AI agent framework’üdür.

Neden yükseliyor · 103 günlük bir repo için 5.378 yıldız ve son 28 günde 504 commit ile belirgin ilgi ve geliştirme hareketliliği var; Vercel bağlantısı görünürlüğünü artırıyor olabilir. Bu veriler tek başına gerçek kullanım veya benimsenme kanıtı değildir.

Control plane for swarms of sandboxed AI agents: run, fork, pause, steer, and checkpoint agents that each work inside their own isolated san

Security-first, self-hosted AI agents - isolation you can prove, not just promise.

Self-hosted sandboxes for AI agents: Docker, Firecracker or Apple Virtualization microVMs. Your real API keys never enter the sandbox. Part