Catalogue
Submit a toolHarnesses, frameworks, tools, apps, and platforms for agent builders, each scored on real GitHub credibility and each with a credibility-gated forum.
47 tools · showing 1–24
PlatformDeno
DeploymentSecurity
denoland
JavaScript/TypeScript runtime with capability-based permissions, used to sandbox agent-executed code and tools.
sandboxpermissionv8browser
FrameworkOpenAI Agents SDK
CodingVoiceSecurity
openai
Python framework for multi-agent workflows with handoffs, guardrails, sessions, sandbox and voice agents, and built-in tracing
multi-agentguardrailsobservabilitysandbox
ToolOpenSandbox
DeploymentCoding
opensandbox-group
If you're adopting coding agents at work, OpenSandbox gives you the runtime layer: one API, `osb` CLI, MCP server, Docke
sandboxcode-interpreterkubernetesdocker
PlatformOpenShell
SecurityDeployment
NVIDIA
Sandboxed runtime for autonomous agents, with declarative YAML policies enforced at the HTTP method and path level
sandboxnetwork-policydockermicrovm
ToolCubeSandbox
Coding
TencentCloud
Instant, Concurrent, Secure & Lightweight Sandbox for AI Agents.
sandboxmicrovmkvmdocker
HarnessMaka
Coding
apache
Apache Maka (Incubating) is a local-first AI agent workspace. Model messages, tool calls, tool results, permission decisions, and terminatio
local-firstdesktopsandboxevent-sourcing
FrameworkCodex
Coding
openai
Lightweight coding agent that runs in your terminal
coding-agentclisandboxide-extension
PlatformOmnigent
CodingSecurity
omnigent-ai
Open-source meta-harness that orchestrates Claude Code, Codex, Cursor, and custom agents behind one interface with policies and sandboxing
codexmulti-agentgovernancesandbox
PlatformE2B
CodingSecurity
e2b-dev
Runs AI-generated code in isolated cloud sandboxes controlled from JavaScript or Python SDKs
sandboxcode-interpreterfirecrackercloud
ToolCode Interpreter
Coding
e2b-dev
Run AI-generated code in secure isolated cloud sandboxes via a JavaScript or Python SDK
sandboxsdkcode-executionjupyter
HarnessDeerFlow
ResearchMemory
bytedance
DeerFlow 2.0 is ByteDance's open-source super-agent harness.
productivitymulti-agentdeep-researchsandboxskill
HarnessNanoClaw
SecurityConnectors
nanocoai
Personal AI assistant that runs agents in isolated Docker containers, kept to a codebase small enough to read and fork
dockersandboxlocal-firsttelegram
PlatformHarbor
QADeployment
harbor-framework
Framework and infrastructure for running arbitrary agents (Claude Code, OpenHands, Codex CLI) in thousands of parallel sandboxed environments for evaluation and RL rollout generation.
evaluationsandboxreinforcement-learningcli
ToolAgent Governance Toolkit
SecurityMonitoring
microsoft
Policy enforcement, zero-trust identity, execution sandboxing, and audit logging for autonomous AI agents across frameworks and languages
zero-trustsandboxgovernanceowasp
ToolAgentConnect
ConnectorsCoding
agentconnect-md
Tag any agent, wherever work happens, your agents work alongside your team and each other, learning as they go.
multi-agentslacksandboxgithub
ToolDeepSeek Harness
Coding
deepseek-ai
DeepSeek open-sourced its full agent harness built so every capability is a plugin. You can swap the loop, the sandbox,
plugindeepseekguisandbox
ToolForkd
Deployment
deeplethe
Agent sandboxes need VM-grade isolation without booting a fresh VM every time.
sandboxmicrovmfirecrackercopy-on-write
PlatformCua
InterfaceDeployment
trycua
Open-source sandboxes, cross-OS desktop drivers, SDKs, MCP server and benchmarks for computer-use agents.
computer-usesandboxmacoswindows
ToolArcBox
DeploymentSecurity
arcboxlabs
Run AI agents on real and isolated machines — own kernel, filesystem, and network — with <100ms boot. Local first, OCI compatible, pure Rust
microvmsandboxdockermacos
HarnessNemoClaw
SecurityDeployment
NVIDIA
NVIDIA reference stack running OpenClaw, Hermes, or Deep Agents inside OpenShell sandboxes with managed inference and network policy
openshellsandbox
ToolrLLM
TrainingQA
rllm-org
rLLM bolts RL onto agents you already wrote. verl, trlx, OpenRLHF make you rewrite the agent into their pipeline. A deco
reinforcement-learningagent-trainingsandboxdistributed-training
ToolAgenvoy
Coding
agenvoy
Make AI actually work for you - A personal agent that writes its own tools and repairs itself.
productivitytool-generationself-improvementsandboxlocal-first
PlatformModal
DeploymentInference
modal-labs
Serverless GPU/CPU cloud for inference, sandboxes and agent workloads.
serverlessgpusandboxautoscaling
ToolOpencode Sandbox Plugin
Security
isanchez31
An OpenCode plugin that sandboxes agent-executed commands using @anthropic-ai/sandbox-runtime
sandboxseatbeltcoding-agent