Codeium
AgentDesktop command center for running multiple AI coding agents locally or in the cloud
- Freemium
- Hosted agent
- Generative code
Desktop command center for running multiple AI coding agents locally or in the cloud

Skills, hooks, memory and security layer for coding agent harnesses
Let a coding agent build diagrams, Mermaid and Markdown cards on a DrawlyHub board
Not checked yetEncrypted vault for .env files with scoped, audited MCP access for coding agents
Dependency-ordered task graph that your coding agent pulls one scoped task from
Keep parallel AI coding agents from overwriting each other on one codebase
Stores every fix your coding agent makes and brings it back when the problem returns
Runs locallyMCP server that tells a coding agent which AI model to call and what to connect
Index code by symbol so agents fetch one function instead of whole files
Runs locallyLet your coding agent ask a vetted human developer for help, only after you approve
Check SWE-bench tasks for leaked fixes: tier, quoted evidence and fix-commit date
Checks OpenAI, Anthropic and Google model IDs for retirement dates before agents use them
Runs locallyCheck, translate and fix app localization files from a coding agent
Runs locallyRemote MCP server for building and calling small task-specific models from an agent

Read, write and organise your Falconer knowledge base from Claude Code, Cursor or Codex
Shared index of verified coding failures and fixes that agents query before retrying
Runs locallyUpload screenshots and files from coding agents and attach them to GitHub PRs
Plan and run drills that test AI agents against synthetic users and cloud worlds
Not checked yetCode graph MCP server that indexes your repo once so agents stop re-reading files
Runs locallyArchitecture graphs parsed from your infrastructure code, for coding agents
Runs locally
Product planning workspace where AI coding agents pull tasks, releases and feedback
Not checked yetLet a coding agent design on a real vector canvas in the Brilliant design app
Runs locallyPersistent project memory and Python verification MCP server for coding agents
Not checked yetHands off a coding agent's session facts so the next agent can continue the work
Runs locallyYour coding agent records narrated demo videos of your app, which tday voices and renders
Runs locallyRecord narrated product demos with your coding agent and have tday voice and finish them
Not checked yetDated registry of API traps for coding agents, plus a local scan of your dependencies
Not checked yetShared board where coding agents log tasks and progress across your projects
Not checked yetShared local memory and handoffs across coding assistants, plus OpenAPI merge checks
Runs locallyCapture coding-agent sessions and resume them in another agent
Not checked yet