An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.
Repository Index
47,133 repositories indexed
1–24 of 27 · Most stars
Free, local plugin that keeps tool output out of your coding agent's context window. Sandbox and SQLite FTS5 search, 99% fewer bytes in context. Works with Claude Code, Codex, Pi, OpenCode, Gemini CLI, Copilot CLI and 4 more agents. Zero telemetry.
- claude
- claude-code
- claude-code-plugins
- mcp
Scale computer-use 2.0 with open-source drivers, cross-OS sandboxes, and benchmarks for training, evaluation, and data generation.
- apple
- cua
- lume
- macos
Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.
Run agents like Hermes, LangChain Deep Agents, and OpenClaw more securely inside NVIDIA OpenShell with managed inference
Secure, Fast, and Extensible Sandbox runtime for AI agents.
- ai
- ai-infra
- kubernetes
- sandbox
Personal memory across agents
- mcp
- memory
- sandbox
- agent-memory
Astrid is a portable, capability-secure operating system for composable software.
Open-source Grok Bot alternative. Choose your own model and sandbox.
Robust, fast, scalable, and sandboxed open-source online code execution system for humans and AI.
- online-judge
- online-compiler
- competitive-programming
- code-executor
Ephemeral Workspaces, durable shared history. LayerFS gives every agent a complete, writable filesystem Workspace over shared committed history, without copying the base. Agents work in parallel, commit what changed as deduplicated checkpoints, then branch, rewind or merge. Try it with LayerFS × DSH.
- agent-infrastructure
- ai-agents
- checkpoint
- content-addressable-storage
Sandboxed Platform for Agentic Code Execution: pluggable-runtime sandboxes for running agent and user code in isolation.
Cross-Platform Micro-VM Sandbox for Agentic Workloads
- agentic-coding
- agentic-engineering
- agentic-workflows
- microvm
Give the agent a machine. Just not yours. Each AI coding agent gets its own isolated machine with root, Docker, and systemd - active defense detects and stops threats automatically.
100% free, open-source personal agents for your messaging apps, tools, and services
Lightweight, agent-native sandboxing with diff, commit and abort
- agent-sandbox
- dsh-plugin
- harness
- pi-plugin
Open source autonomous engineering harness in your cloud. One sandbox per task, no real secrets inside.
- agent-harness
- agent-sandbox
- agent-security
- agentic-coding
CRAB (Clean Rebuild of Anything's Behavior): rebuild software from behavior, not source code. An MCP-powered toolkit for black-box observation, clean-room reimplementation, and behavioral verification.
- clean-room-reimplementation
- ai-agents
- behavioral-testing
- black-box-testing
A token efficient, local LLM friendly agentic coding harness: a complete agent runtime (agent loop, tool pipeline, sandboxing, session persistence) with four front-ends — a Blazor web UI, a headless CLI, and JSON-RPC / ACP stdio servers for editors and automation.
- agent
- agentic-ai
- agents
- coding
Nosis is a lightweight personal agent runtime: per-session execution boundaries with OS-level sandboxing, computer use, a full built-in toolset, Skill / Plugin / MCP extensions, one runtime shared by GUI and TUI, and file-persisted sessions, plans, and memory.
- agent-framework
- agent-runtime
- agent-skills
- ai-agent
Airut is a system for running Claude Code tasks from email and Slack. It handles workspace provisioning, container isolation, network sandboxing, session persistence, and cleanup — a secure foundation for autonomous agentic development.
CLI tool for running coding agents inside hardware-isolated microVMs
Sandboxed devcontainer for running Claude Code, Codex, and OpenCode in bypass / auto-approve mode.
- ai
- claude-code
- codex
- devcontainer
Give the agent a cage, not your keys. One-command Docker sandbox for AI coding agents: full autonomous permissions, per-project isolation, your host stays untouched.