⌘Langbase

Keyboard shortcut Ctrl+t to toggle Taste in CommandCode

Namespace/package support for Taste pull and push commands

Changelog has RSS feed support

Combined the changelog/all and changelog/major.minor.page into a single changelog/all page

CommandCode Organizations for team collaboration with multi-tenancy support

CommandCode Taste Package Sync to push and pull learnings across devices

CommandCode API Keys page for managing authentication tokens

CommandCode light mode support with full theme switching

CommandCode auto-update feature with installation notifications

Organization owner change functionality in Langbase Studio

CommandCode queued messages design improvements

CommandCode new taste feed ui

CommandCode Billing improvements with Stripe integration and invoice management

CommandCode improved onboarding with context-aware CTAs for returning users

CommandCode Taste learning improvements with project-level guardrails

Improved CommandCode profile switcher for navigating between user and org accounts

Improved CommandCode settings pages with better UX

Fixed CommandCode OAuth authentication issues

How to Build AI Agent guides for Claude 4.5 Sonnet, Gemini 2.5 Pro, GPT-5, Kimi K2, Llama 3.3

CommandCode beta version launched

Claude Haiku 4.5 model is now available on Langbase

CommandCode Memory feature for remembering project context across sessions

CommandCode Custom Agents to create and execute specialized AI agents

CommandCode Auto-Compacting conversations when context window fills

CommandCode Taste Learning V2 with dedicated learning agent infra

CommandCode Landing Page with responsive design and light mode support

CommandCode Custom Commands for frequently used prompts and workflows

CommandCode Custom Agents generation through AI

CommandCode Agent details and management UI

CommandCode pre-approve read-only commands for faster execution

CommandCode tool output expansion with Ctrl+O hotkey

CommandCode whoami command

CommandCode tool call blocks in UI

CommandCode responsive UI that adjusts on terminal resize

CommandCode compact conversation slash command

Azure OpenAI models including GPT-5 series, o3, o4-mini, and GPT-4.1 series

Image Generation API with support for OpenAI, OpenRouter, Together AI, and Google

Image models: gpt-image-1, dall-e-3, dall-e-2, flux models, and imagen-3.0

Image generation pricing with quality and size multipliers

Image usage tracking and cost calculation

Azure OpenAI model selector with hover cards in Studio

Quickstart tracking with Time to First Request analytics

Subscription cancellation feedback sent to Slack

CommandCode Shell command parsing improvements with shell-quote

CommandCode error handling with automatic retries

CommandCode share context improvements

CommandCode taste settings improvements

Improved Usage page with better organization memory calculation

Improved Azure OpenAI integration with backward compatibility

Improved Azure LLM Keyset with model selection component

Fixed Claude 4 models temperature/top_p parameter conflict

Claude Sonnet 4.5 model is now available on Langbase

MCP HTTP Streamable support in agent.run

Quickstart in Langbase Studio

CommandCode Taste Learning System for continuous learning from interactions

CommandCode Web Search and WebFetch tools

CommandCode Provider selector for switching AI models

Azure OpenAI models with reasoning support

Reasoning support for Claude Sonnet 4.5

Improved Usage page with organization support

Replaced Intercom with custom support button

Fixed JSON mode for Azure OpenAI models

Fixed CommandCode auth and credit check issues

Fixed empty thread creation

Fixed Usage page stats for organizations

Developer Series blog: "Building a Slack Insight Agent"

Blog: "Building an AI-powered news app with Langbase SDK"

CommandCode platform launch with Organizations, Billing, Authentication, and Web Studio

DeepSeek v3.1 is now available on Langbase

Unified support of reasoning params for reasoning models

Reasoning config in Langbase Studio

GPT-5 models are now available on Langbase

Claude Opus 4.1 is now available on Langbase

OpenAI's open source models are now available on Langbase

Community in Command.new is live

Traces in Command.new

Improved Runs UI in Studio

Improved Python SDK errors

Fixed creation of empty threads when store messages is off

Fixed Memory deletion lag

Langbase Python SDK is now available on PyPI

More agent examples are now available on Command.new

Moonshot Kimi K2 is now available on Langbase

Tracing support is now available on Command.new

Full screen agent flow support is now available on Command.new

Download project is available on Command.new

Slack MCP server support is now available on Agent primitive on Langbase

Grok 4 model is now available on Langbase

Chai.new is now Command.new

Langbase blog redesign is now live

Fixed Agent app crashing while typing in the input box on Command.new

Contributors section on Pipes and Memory pages is now available

Qwen 3 is now available on Langbase

Chai now supports light mode

Pixtral by Mistral AI is now available on Langbase

Public code agent privacy status is now available on Chai.new

Stop agent app generation is now available on Chai.new

Archive agent is now available on Chai.new

Qwen2.5 Vision is now available on Langbase

Llama 3.2 Vision models (70B and 11B) are now available on Langbase

Langbase careers page is now available

Gemini 2.5 Flash Lite is now available on Langbase

Stable Gemini 2.5 Pro and 2.5 Flash are now available on Langbase

Magistral by Mistral AI is now available on Langbase

Gemini 2.5 Pro Preview 06-05 is now available on Langbase

Delete thread messages support is now available on Chai.new

Agent readme is now available on Chai.new

Command + K menu is now available on Chai.new

Agent app code versioning is now available on Chai.new

Firecrawl support in Crawler AI primitive is now available on Langbase

Langbase Tools are now available on our SDK and API as an AI Primitive

Runtime Agents — an AI Primitive by Langbase is now available on our SDK and API

Threads — an AI Primitive by Langbase is now available on our SDK and API

Embed — an AI Primitive by Langbase is now available on our SDK and API

Workflow — an AI Primitive by Langbase is now available on our SDK and API

Chunker — an AI Primitive by Langbase is now available on our SDK and API

Parser — an AI Primitive by Langbase is now available on our SDK and API

Chai.new — Vibe code AI Agents to production

Gemini 2.5 Flash Preview is now available on Langbase

OpenAI o4-mini is now available on Langbase

OpenAI o3 is now available on Langbase

GPT 4.1 models are now available on Langbase

GPT 4.1 models are now available on Langbase

Mistral Small is now available on Langbase

Azure OpenAI gpt-4.5 is now available on Langbase

Grok 3 models via OpenRouter are now available on Langbase

Grok 3 models via XAI are now available on Langbase

Llama 4 Scout and Maverick models support via Together AI, Groq and Fireworks AI

Google 2.5 Pro Gemini model support

Google Gemini 2.5 Pro support

chunkSize and chunkOverlap configuration for Memory

TopK configuration for memory

Structured outputs support

Show total memories on user/org profile page

Enable streaming for OpenAI o1 model

Threads v1 API endpoint

Llama-Guard-3-8B moderation model

Display user email on settings page

User/org subscription status on profile in studio

Improved UI for Prompt, Input and Completion in Runs table

Handle unsupported params for Google function call

Default values for tool_choice and parallel tool calls on Pipe create

Fixed parallel tool call edge case for some providers

Fixed filter types in SDK

Update memory name in pipe versions on memory name update

Filters examples for Langbase SDK

Google gemini-2.0-flash-lite model support

EU API base url support in Langbase SDK

Messages v1 API endpoint

getToolsFromRun and getToolsFromRunStream helper functions in Langbase SDK

Pass memory to pipe run v1 endpoint on runtime

OpenAI gpt-4.5 model support

usePipe support in Langbase SDK

Set default max tokens to 2048

EU region support for Langbase

OpenAI chatgpt-4o-latest model support

LLM API v1 endpoint

AIE summit custom signup

Parser API v1 endpoint

Onboarding experience

Langbase SDK syntax

Improve observability of pipe run v1 endpoint

Deprecate Perplexity llama models

Revamp of Langbase Customers page

Add source in /meet page

Update About page item placement

Fix embedding model key check on API

Fixed thread id in non-stream pipe run

Cieled token count in Pipe IDE

Azure OpenAI models support

Fixed pipe not found error

Site crash on auth pages

Liquid Web customer study

Langbase CLI

Retry option on documents table

Token count in playground

Copy prompt and completion buttions in single run log

Add embedding model selector for memory creation in studio

OpenAI o3-mini model support

Crawler API v1 endpoint

Web search API v1 endpoint

Filter support in memory retrieve endpoint

Document search in single memory for enterprises

List numbers of document pages on pricing page

Embed API v1 endpoint

Threads v2 architecture

Perplexity sonar and sonar pro models are now supported by Langbase

DeepSeek R1 is now supported by Langbase

Chunk API v1 endpoint

DeepSeek API as a provider is now supported by Langbase

DeepSeek v3 via Together is now supported by Langbase

DeepSeek v3 via Fireworks is now supported by Langbase

Custom LLM API key header support

Request trace ID in pipe run

Improve playground run request latency

Improved playground error messages

Disabled stream for OpenAI o1 model

Improve pipe run API latency

Wrap prompt and completions in single run logs

Redirect /langbase-sdk to /sdk in docs

Default entity API keys

Shipped billing improvements

Fix refresh button in run table

Org subscription status on studio

Run usage unit

Fixed user login lowercase inconsistency

Fixed Chat UI overflow issue

OpenAI's o1-2024-12-17 model support.

Web Search with AI Agents guide.

Cohere's embed-multilingual-v3.0 embedding model support on API.

Cohere's embed-multilingual-light-v3.0 embedding model support on API.

Google's text-embedding-004 embedding model support on API.

State of AI Agents 2024 banner on Studio & Docs

Published 2024 State of AI Agents study

Llama 3.3 models are now supported by Langbase

Shipped keyset bar in Pipe IDE

Pass tools in run API endpoint and SDK

Shipped preview URLs for guides, blog, and customer stories

Blog: Developers Drop GPT-4o Mini in a Flash On Langbase: Google’s Gemini is Faster, Cheaper, Better

Shipped memorysets/** → memory/** & added redirects

Shipped documentName parameter in memory API endpoints

Shipped retry mechanism for fetching thread from database

Fixed sidebar trigger on mobile view for customer stories

Fix $ sign being rendered as code snippet in markdown

Fixed LLM key error in memory page

Save LLM tool calls as completion tokens

Search bar inside memory page

Shipped tooltips on pricing page

Shipped API v1 support in Langbase SDK

Shipped docs agent chatbot component

Shipped syntax highlight in learn content

Google sign up support

Syntax highlighting for code snippets in Langbase guides

Vision support is live on API for different providers

OpenAI o1 models now support streaming

gpt-4o-2024-11-20 is available on Langbase

Shipped sign up ban with disposable email addresses

Improved profile switcher design

Improved sidebar design

Improved model selector UI

Improved API rate limits of Pro users to 300 requests per minute

Improved pro plan rate limits to 300 requests per minute

Fixed 500 API error if no LLM keys

Fixed Anthropic model streaming

Fixed mobile view of changelog all

Fixed studio favicon

Fix guides CTA for light mode

Langbase meet page is now available

xAI models tool call support is now available

Tool call support for TogetherAI models that support tool calls

Tool call support for Anthropic and Google provider models

Gemini Flash 8B model is now available on Langbase

Llama 3.2 models are now supported by Langbase.

API v1 is now available

Langbase status page

Content infrastructure v2 with central content repository

Decrease minimum username length to 4 characters

Optimize pipes stats query processing time from 83ms to 6ms

Fix model pages, blog, changelog and guides SEO

Fix object storage endpoint validation

Fix LLM response parsing when completion and tool call both exists

Fix token calculation on tool call

Fix username update issues for few users

Run endpoint is live. It replaces the old Generate and Chat endpoints

Support for OpenAI o1 models with handling of its special cases

Llama 3.1 models are now supported by Langbase

Model Pages are now available. One place to get latest details of LLMs

Threads. You can now view all the threads and conversation history of your pipes

Mistral AI models are now supported by Langbase

Improved CRUD API performance by 10x using object storage

Update model costs, deprecate Together's deprecated models

Improved memory deletion

Merged Chat and Generate Pipes. Now you can chat and generate in the same pipe

Improved order of messages in threads

Fixed docs file icons in memory

Fix playground timed out for long running requests (>40 secs). New timeout is upto 4 mins

Blog: Netlify uses Langbase to bring GeoCities Back to Life

Langbase Blog

Terms & Conditions and Privacy Policy are now available

Perplexity models

gpt-4o-2024-08-06 model

JSON mode in Gemini models

Pricing page is now available

video=open param to open launch video on landing page

CMD + S keyboard shortcut on landing page to redirect to sign up

Pipes page is now available

Improve studio sidebar design

Remove unnecessary icon sets and improve icons in studio

gpt-4o-min as default model in new pipes

Deprecate qwen72 and add yi-large models

Explore page ranking algorithm

Preserve period (.) in pipe name

Promisify sign in page toasts

Improve studio sidebar watch demo button

Anchor keysets section in user/org settings

Internal reserved words

Improve onboarding next steps

Added failed run reason in Usage

Pricing page get started link now works correctly

Pipe readme links format properly

Fork pipe now also fork its functions

Dead links after pipe rename

Redirect to landing page after pipe delete

rag.new and pipe.new redirect fix when logged out

Fix error parsing in Google Gemini responses

Fix Pipe meta design

Explore page to showcase Open AI pipes

rag.new to create a new memory on Langbase

Together Llama 3.1 support

Fireworks provider support

Together Gemma 2b and 7B support

GPT-4o mini and Gemma 2 support

Stream flag support in API

Remove waitlist from dashboard

Update all dashboard dependencies to latest versions

Auto-redirect to new pipe/memory after creation

Fix JSON mode on gpt-4o-mini

RAG and JSON prompts now switching correctly with every version

⌘ Langbase SDK Examples` for Node.js and Next.js

⌘ Langbase SDK generateText() API reference

⌘ Langbase SDK streamText() API reference

Stream and stream-off code snippets inside Pipe API page

⌘ Langbase TypeScript SDK is now available