AI Developer Tool · JavaScript

fleet

One API for every agent pod: starts a pod on the cheapest sandbox provider you have a key for, and moves on when one fails. https://fleet.flisk.si

flisk@flisk-sh · Atlas 70.7 · #9= builder

View on GitHub1 Open flisk's Atlas

An organisation's project: the project boards rank individual builders, so it is shown here without a rank. Among builders' projects it would sit 28th in AI Agents.

What it is

Fleet is a unified API service for running agent code in sandboxed Linux environments across multiple providers, featuring automated failover, encrypted key management, a web console, and MCP server integration for agent tool use.

agent-infrastructure
ai-agents
blaxel
cloudflare-workers
code-execution
daytona
mcp
mcp-server
sandbox

Scored atd97345313 Nov 2026Changes since

Merit describes the code at this commit. Later pushes count once the owner rescans. How merit is scored

Where it counts

AI Agents100%
MLOps20%

How much of the project is about each field, as scoring counts it. It ranks in the field it is most about.

What the judge found

Read from the project's code at its scored commit.

Strengths4

Unified multi-provider sandbox abstraction with automated failover
Strong test coverage and CI ensuring reliability
Clear documentation and extension guidelines for adding providers
MCP server integration enabling agent tool use

Limitations

The owner keeps this project's limitations private.

Where it would sit on the AI Agents board

Whole board

RankProjectBuilderFieldMerit