TanStack
Featured
router
TanStack Router is a type-safe, data-driven React router with built-in caching, prefetching, and nested layouts, while TanStack Start extends it into a full-stack SSR framework.
managed-agents
managed-agents is an open-source, local-first runtime layer for building and operating self-hosted AI agents with sessions, tools, approvals, sandboxed execution, memory, credential vaults, audit trails, and a Claude-compatible Console and API.
Stars
363
7-day growth
No data
Forks
32
Open issues
0
License
NOASSERTION
Last updated
2026-07-24
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It provides a production-ready control plane for AI agents that is local-first, open-source, and model-agnostic, addressing the gap between agent SDKs and full runtime infrastructure without vendor lock-in.
Who it is for
- Enterprise AI teams building self-hosted agent platforms
- Developers prototyping production-grade agent workflows
- Teams needing auditable, sandboxed agent execution with local data control
- Integrators embedding agent runtimes into desktop or internal tools
Use cases
- Running a local Claude Managed Agents-style Console for agent development
- Building self-hosted enterprise AI agents with auditable sessions and tool calls
- Prototyping customer support, incident response, or research agents
- Packaging reusable agent templates, MCP connectors, and skills for field deployments
Strengths
- SQLite-backed metadata store with runtime state outside the project directory
- Resumable Server-Sent Events for session timelines, debugging, audit, and replay
- Built-in credential vault with encrypted storage and network-scoped injection
- Open-source (Apache-2.0) with a Claude Managed Agents-compatible API and SDK
Considerations
- Requires Node.js 22+ and npm 10+; requires a configured model vendor API key
- Local-first design with SQLite only; no built-in cloud or distributed storage
- Advanced sandbox execution (Docker) is optional and not enabled by default
README quick start
managed-agents
SandBase managed-agents is the safe, local-first runtime layer for enterprise AI agents.
managed-agents helps teams move AI agents from demos to production with
runtime infrastructure for sessions, tools, approvals, sandboxed execution,
memory, credential vaults, audit trails, replayable events, and operational
visibility. It exposes a Claude Managed Agents-compatible Console and /v1
resource API while keeping runtime metadata in SQLite outside your project by
default.
Use it to build and operate self-hosted AI agents, local developer agents, desktop agent runtimes, MCP-enabled workflows, and enterprise proofs of concept without locking your runtime layer to a single model provider.
Why managed-agents?
Agent SDKs are great for writing an agent loop. Production agents need more: state, session history, tool governance, sandbox boundaries, credential handling, memory, auditability, and a Console for humans to inspect what happened.
managed-agents focuses on that runtime layer. It is not a visual workflow
builder and it is not another model SDK. It is an open-source control plane for
running, observing, and governing AI agents locally or in self-hosted
environments.
Features
- Claude Managed Agents-style Console and
/v1resource APIs - SQLite-backed agents, skills, sessions, environments, credential vaults, memory stores, API keys, and file metadata
- Resumable Server-Sent Events for session timelines, debugging, audit, and replay
- File resources, memory stores, credential vaults, and environment templates
- local file/skill bytes stored outside the source checkout by default
- One active model provider boundary configured through Settings
- Local API keys and bearer-token authentication for shared local runtimes
- Optional seed/import folders for
agents/*.yamlandskills/*/SKILL.md - Local sandbox execution by default, with advanced sandbox adapters configured only when available
- MCP toolsets, built-in tools, permission policies, and skill packages
- One configured model vendor boundary with adapter-owned model defaults
- Optional TypeScript convenience SDK at
managed-agents/sdk
Common Use Cases
- Run a local Claude Managed Agents-style Console for agent development
- Build self-hosted enterprise AI agents with auditable sessions and tool calls
- Prototype customer support, incident response, researc
Description
Open-source CMA-compatible agent runtime. Run multi-agent systems locally with any model (Ollama/vLLM/Claude/GPT), MCP tools, scenario templates, and a beautiful dashboard. One command start. Built for enterprise teams.
Related repositories
Similar projects matched by category, topics, and programming language.
vercel-labs
Featured
scriptc
scriptc compiles ordinary TypeScript into small, fast native executables without needing Node.js, V8, or any JavaScript runtime in the binary.
Jakubantalik
Featured
thinking-orbs
A React component library that renders six hand-tuned animated thought orb loading indicators on a plain 2D canvas, with two purpose-tuned sizes and automatic theme detection for AI and agent UIs.