# Letta Code Agent runtime with persistent memory for coding and general tasks. Agents can be reused through CLI, desktop, browser and messaging channels. Canonical profile: https://agenten-kompass.mmeierhoff.chatgpt.site/en/agents/letta-code/ Editor: [Michael Meierhoff](https://agenten-kompass.mmeierhoff.chatgpt.site/en/about/) Sources reviewed: 2026-10-10 Basis: provider documentation. Examples are editorial suggestions, not hands-on product tests. ## Overview Letta Code connects a local agent runtime with persistent agent state. Letta Cloud is the default backend; a local backend can be selected at startup. - Provider: Letta - Product family: Letta Code - Profile type: General-purpose agent with persistent state - Environment: Local CLI, desktop for macOS, Windows and Linux; browser and connected computers - Connections: Files, shell, MemFS, skills, Slack, Telegram, Discord and custom channels - Setup: Install CLI or desktop, select a local or cloud backend and configure model access and tool permissions - Pricing model: Free USD 0/month, Pro USD 20/month; additional model usage and API consumption charged separately ## Operation & oversight Operational details for this profile have not yet been researched. ## Provider Letta develops Letta Code and the cloud platform for agents with persistent memory. The repository is maintained by the team behind MemGPT. - Operator: Letta - Organization: Company - Website: https://www.letta.com/ - Reviewed: 2026-10-10 - Provider source: https://github.com/letta-ai/letta-code - Provider source: https://docs.letta.com/pricing ## Prices and included usage Pricing checked: 2026-10-10 Personal plans separate the base price and Letta Auto quota from overage. Your own model keys are billed by the model provider. ### Free USD 0/month Three stateful agents, limited Letta Auto and your own API keys or external coding plans. Price source: https://docs.letta.com/pricing ### Pro USD 20/month Up to 20 stateful agents and weekly and monthly Letta Auto quota; usage-based overage. Price source: https://docs.letta.com/pricing ### Teams Pro USD 20/seat/month Shared agents, access control and Letta Auto quota. Price source: https://docs.letta.com/pricing ### API Plan USD 20/month plus usage Unlimited agents; USD 0.10 per active agent/month, USD 0.00015/second of server-side tool execution and model costs. Price source: https://docs.letta.com/pricing The specific Letta Auto quota is not publicly quantified; check current allowances in the account. The Apache-2.0 runtime and a local backend have their own operating and model costs. Client-side CLI tools incur no Letta CPU charge according to the pricing documentation. Pricing details: https://docs.letta.com/pricing ## Key features ### Manage memory in Git MemFS represents agent memory as an editable Git filesystem with version history. Source: https://docs.letta.com/concepts/memfs ### Continue agents across interfaces CLI, desktop and browser access the same agents in the selected Letta account. Source: https://github.com/letta-ai/letta-code ### Use persistent skills Skills can belong to the project, computer or agent memory and provide relevant resources and scripts. Source: https://docs.letta.com/configuration/skills ### Schedule tasks One-time or recurring prompts run locally with an active session or as cloud schedules in a sandbox context. Source: https://docs.letta.com/configuration/schedules ### Set tool permission levels standard, acceptEdits, strict and unrestricted control approvals; additional allow and deny rules restrict actions. Source: https://docs.letta.com/configuration/permissions ## Requirements and limits ### Interactive CLI starts with broad autonomy Limitation: The interactive CLI defaults to unrestricted. Select standard or strict for individual approvals before shell commands, edits and subagents. Source: https://docs.letta.com/configuration/permissions ### Local schedules need a running process Limitation: Local schedules run only while a Letta app, CLI or server process is open. Cloud schedules use UTC and may fall back to the sandbox when the target computer is offline. Source: https://docs.letta.com/configuration/schedules ### Distinguish cloud state and local backups Limitation: Cloud agents store memory, identity and conversations with Letta. Users are responsible for backing up local MemFS repositories. Source: https://docs.letta.com/concepts/memfs ### Check quotas and overage Limitation: Free includes three stateful agents, Pro up to 20. Letta Auto quotas are described without a specific public token allowance; overage is paid. Source: https://docs.letta.com/pricing ## Example workflows ### Maintain project knowledge across sessions - Your input: Project materials, verified facts and rules for persistent memory. - Possible result: An agent that reuses saved project knowledge in later tasks. - What to check: Check saved facts, memory changes and the backend storage location. ### Set up a recurring check - Your input: A bounded check, schedule and reachable target computer. - Possible result: Recurring check reports in the selected agent context. - What to check: Check the running process, time zone, execution target and spending limit. ## Context Select backend and permissions before starting. Local schedules require an active Letta runtime; model consumption may exceed the plan price. Official product documentation reviewed. Workflows and assessments are editorial; hands-on product tests are outside the scope of this directory. ## Sources - https://github.com/letta-ai/letta-code - https://docs.letta.com/pricing - https://docs.letta.com/concepts/memfs - https://docs.letta.com/configuration/skills - https://docs.letta.com/configuration/schedules - https://docs.letta.com/configuration/permissions [Sources and method](https://agenten-kompass.mmeierhoff.chatgpt.site/en/sources/)