Changelog

​

New region

• Added a new region in the European Union: eu-fra-1 (Frankfurt)

​

Improved build control for sandbox images

• Added ability to opt-out of our automatic slimming process for sandbox images, by setting slim = false.

​

Public access for agents on Mark 3 infrastructure

• Added support to expose agents publicly without authentication on Mark 3 infrastructure.

​

Support for in-place upgrade of sandbox API (beta)

• Added an SDK method to upgrade a sandbox’s API without needing to restart or recreate it.
• Only available for sandboxes created with sandbox API v0.2.0 or later (sandboxes created after 2 Feb 2026)

​

Clearer visibility of sandbox expiry time

• Added new read-only parameter, expires_in, to sandbox metadata that computes the exact date and time when a sandbox will terminate due to its TTL or lifecycle policy.

​

Improvements to sandbox process management and logging

• Added ability to view logs for specific processes within a sandbox: bl logs sandbox my-sandbox my-process
• Support for real-time log streaming with -f/--follow flag for sandbox processes (similar to tail -f)
• Added new command to list processes in a sandbox: bl get sandbox my-sandbox process (or bl get sbx my-sandbox ps)
• New .oyaml and .ojson output formats for process listings

​

The Big CLI Upgrade

• Added shell completion for CLI commands including workspace, sandbox, job, agent, function, model, volume, policy, and image names
• Tab completion now suggests valid resource names as you type, reducing errors and improving efficiency
• Simplified syntax for filtering job logs by execution and task: bl logs job my-job <execution-id> <task-id>
• New token refresh functionality for authentication operations: bl token
• Various bug fixes and documentation improvements

​

Additional metrics for batch jobs in Blaxel Console

​

Support for job resource overrides

​

Improved sandbox creation time

​

Support for volume resizing and sandbox expiry modification

• Added an SDK method to increase the size of a volume.
• Added SDK methods to update sandbox time-to-live and expiration policies after the sandbox has been created.

​

Go SDK released

​

Improved terminal interface for sandboxes

​

New API reference

​

Support for sandbox and volume labels

​

New API endpoint for public IP address retrieval

​

New find() and grep() SDK methods

​

Browser-based terminal for sandboxes

​

New Jobs API endpoints and SDK methods

​

Deprecation of BL_SERVER_HOST and BL_SERVER_PORT variables

​

Asynchronous triggers for agents on Mark 3 infrastructure

• Added support for asynchronous requests for agents deployed on Mark 3 infrastructure.

​

Manual validation for CLI login

​

Revision management

• Added support for storing the last 5 revisions for agents, MCPs, models and batch jobs deployed on Mark 3 infrastructure. Revisions are deployed using the blue-green deployment strategy. This enables rollbacks and progressive rollout strategies (e.g. canary deployments).

​

New Console sidebar

​

Process restart on failure

• Added support for restarting a sandbox process if it fails, up to a maximum number of restart attempts.

​

Relace support

​

Binary support for sandboxes

• Added readBinary() function for sandbox filesystem to return a file content as a standard Blob object
• Added writeBinary() function for sandbox filesystem to write a Buffer/Blob
• Added download() function to downloads a file from the sandbox’s file system to your local machine.

​

HTTP Stream transport for MCP servers

• HTTP Stream is now the default transport for all MCP servers deployed on Blaxel, following Protocol Revision 2025-03-26.

​

Mk 3 is now the default generation

• Creating a new agent or MCP server without specifying a version → defaults to Mk 3
• Updating an existing Mk 2 agent or MCP server without specifying a version → remains on Mk 2
• Attempting to update a Mk 2 agent or MCP server to Mk 3 → returns an error
• Updating an existing Mk 3 agent or MCP server without specifying a version → remains on Mk 3
• Attempting to downgrade a Mk 3 agent or MCP server to Mk 2 → returns an error

​

Storage pricing

• starting November 7, 2025 for Sandbox Snapshots and Sandbox Volumes.
• starting December 1, 2025 for stored deployment Images.

​

Sandbox volume templates

​

Blaxel Blog

​

Sandbox network v2

​

New sandbox builder

• Our new builder has been successfully rolled out with optimized performance for image downloads and adjusted timeouts.
• Key improvements:
  • Larger image support: Images can now exceed 10GB
  • Optimized file system: Better memory management with in-memory speed
  • Faster startups: Further reduced cold start times
  • Cost efficiency: Overall lower costs due to system optimizations

​

New init command

• bl new agent
• bl new mcp
• bl new job
• bl new sandbox

​

Sandbox lifecycle policies

• expire at a specific date using the expires parameter.
• expire after a total maximum lifetime using the ttl parameter
• expire after a period of inactivity using the lifecycle.expirationPolicies / lifecycle.expiration_policies parameter

​

Billing Explorer

​

New MCP server: Linkup

​

Custom domains

• Added possibility to register a custom domain in your workspace and verify it from Blaxel
• Added support for custom domains for sandboxes previews

​

New MCP server: Nia

​

TTLs on sandboxes

​

Improved sandbox creation time

​

Usage-based pricing model

​

New MCP servers: AgentMail, Context7

• Added new MCP server: AgentMail
• Added new MCP server: Context7
• Added new agent template: Email Support Agent - powered by AgentMail

​

Cron jobs

​

Sandbox tools for codegen

• Added fast apply of file edits powered by MorphLLM for efficient code changes (2000+ tokens/second)
• Added multiple other codegen-optimized functions by making tool calls through the MCP server of a sandbox.

​

Deploy from Dockerfile

​

New MCP server: Airweave

​

Improved latency on sandbox

• Reduced typical duration of sandbox creation down to 4-8 seconds
• Reduced latency on calls made to a sandbox

​

New MCP server: Supabase

​

New Logs console

• Reworked interface of Logs console
• Added ability to filter log queries

​

Sandboxes file system improvements

• Added ability to watch sub-directories
• Added ability to ignore some files/directories from watch
• Added ability to write multiple files at once
• Added ability to write binary content in the fs
• Added ability to get both stderr/stdout logs at once in batch mode

​

OneGrep Integration

​

Sessions for sandboxes

​

New MCP servers: HubSpot & Smartlead

• Added new MCP server: HubSpot
• Added new MCP server: Smartlead

​

Preview URLs for sandboxes

​

Async endpoint for agents

​

Sandboxes

• Boot time under 20ms
• Persistent filesystem across sessions
• Operable via both Python/TypeScript SDK and MCP server

​

New MCP: Tavily

​

New Blaxel Console

​

New framework supported: Google ADK

​

New framework supported: PydanticAI

​

SDK v0.1.0

• Released a new major version of our SDK to give you access to lower-level features:
  • host custom MCP servers
  • connect to LLM via Blaxel gateway
  • connect to tools hosted on Blaxel
• Compatibility with all major agentic frameworks from day 1: LangChain, LangGraph, CrewAI, LlamaIndex, OpenAI Agents, Vercel AI SDK, Mastra.
• Improved cold-starts for agents and functions

​

Functions are now MCP servers

• All functions on Blaxel are now exposed as MCP servers, even custom functions.
• Create a custom MCP server from a scaffolded repo using bl create-mcp-server

​

Templates of agents

• Added 6 templates of agents
• Templates can be used when creating a new agent from the Blaxel Console. Deploying a template will deploy the agent on your GitHub organization and setup a live synchronization watching future updates
• The entire template list is available on our website
• Added information in Blaxel Console that an agent is synchronized via GitHub
• Updated the schema for functions to better match MCP standard

​

Improved build times

​

Voice agents

​

Revisions & canary deployments

• Each build of an object creates a new immutable revision, which can be deployed to redirect request traffic to it
• Ability to deploy a new revision using blue-green strategy
• Ability to rollback to previous revision
• Ability to split a percentage of traffic to a second revision (canary deployments)

​

Beamlit is now Blaxel!

​

Sunsetting environments

​

New pricing plans

​

DeepSeek integration

​

HuggingFace integration

• Connect to public or private models from HuggingFace Inference API (serverless) and Inference Endpoints (dedicated)
• Deploy a model in HuggingFace Inference Endpoints (dedicated)

​

Azure AI Foundry integration

• New integration: Azure AI Services (for OpenAI models and others)
• New integration: Azure Marketplace (for Llama models and others)

​

9 new pre-built toolkits

• Brave Search
• Google Maps
• Slack
• Linear
• AWS SES
• Cloudflare
• PostgreSQL
• AWS S3
• Dall-E

​

Policies on token usage for cost control

​

🚀 We launched Beamlit beta!

• New world-class infrastructure for minimal cold starts and maximum reliability
• World map showing the origin of requests on your agents AI
• Many additional charts

​

Agentic traces

• Added Agent Observability suite, with traces of agents’ requests.
• Added ability to launch a request in debug mode from the Playground to save the trace

​

Latency metric tracking

​

Beamlit extension for VScode

​

New Beamlit console

• Beamlit console has been completely reworked, in order to center the experience around agents and their deployments.
• Removed custom model deployments and renamed external models “model APIs”
• Added statuses for deployments
• Added playbook to deploy an agent from local code in the Beamlit console

​

Visual aspect of charts is improved

• Improved visual aspect of charts and options to change time window of screens
• API reference for agents’, models’ and functions’ deployments has been updated

​

CLI support for running agents and functions

• You can now develop (and run) your own AI agents locally with the Beamlit SDK.
• Use CLI command bl create-agent-app your-agent-name to initialize a repository with the code skeleton to get started
• Use CLI command bl serve --local to run your AI agent on your local machine

• Cohere
• xAI

• https://github.com/beamlit/bl-action

• OpenAI
• Anthropic
• Mistral AI

​

Features

• Agents: run AI agents across multiple locations, so your consumers get the lowest latency and the highest availability.
• Models: connect or deploy generative AI models behind our global gateway, from public endpoints to custom fine-tuned models
• Functions: run serverless functions that provide your agents with the tools to interact with their environment
• Global Inference Network: make your agents available globally and locally with a network designed for AI inferences that optimizes for mission-critical latency while respecting your deployment, routing and cost policies.
• Environments: manage compliance at enterprise level by enforcing policies directly in your development life-cycle
• Policies: define global rules and strategies regarding your deployment placement, inference request routing, and hardware usage.