# Alternatives to Letta > Source: https://theagentsindex.com/letta/alternatives (current datasheets, evidence-ranked) Candidates share the baseline category or are previously researched peers. Requirements, preserved strengths, explicit trade-offs and research coverage decide the order; paid tier does not. ## Shortlist ### 1. Cline Open-source coding agent for VS Code, JetBrains, the terminal and CI, running on whichever model you bring. **Research coverage:** 34/35 criteria **Where it improves on Letta:** - [Writes tests: yes — Test authoring is a named use case, covering unit and integration tests for existing large codebases rather than only tests for code it just wrote.](https://cline.bot/enterprise) - [Whole-codebase work: yes — Repository-wide migrations are a stated use case, though the vendor is explicit that it never indexes a repo and instead uses partial-file analysis and summarisation.](https://cline.bot/) - [MCP server: partial — Cline is an MCP client - you attach local or remote servers to it, and a marketplace lists them - but the vendor documents no MCP server exposing Cline itself to another agent.](https://docs.cline.bot/mcp/mcp-overview) **Trade-offs against Letta:** - [In a browser: partial — The browser UI is Kanban, a board you start yourself on localhost and label a research preview; the vendor's hosted web app is the account and admin console, not a place to run tasks.](https://docs.cline.bot/usage/kanban) [View Cline](https://theagentsindex.com/cline) ### 2. Agno Python SDK, open-source AgentOS runtime and hosted control plane for building and operating agents. **Research coverage:** 35/35 criteria **Where it improves on Letta:** - [MCP server: yes — AgentOS can expose registered agents as an MCP server, so another agent can call them; docs also ship as MCP.](https://docs.agno.com/features/api) - [Seat model: yes — Three seats included on Pro, $30/month per extra seat; no published ceiling.](https://www.agno.com/pricing) - [Pooled budget: partial — There is no metered balance to pool; seats share access to the same connected runtimes and usage inside a connection is unlimited.](https://www.agno.com/pricing) **Trade-offs against Letta:** - [Agent permissions: partial — Runs are unattended unless a tool is marked for approval; then the run pauses in your database until an admin resolves it.](https://docs.agno.com/agent-os/approvals/overview) - [In your pipeline: no — The enumerated serving surfaces are REST, MCP in Claude/ChatGPT and chat apps; no pull-request or CI surface appears.](https://www.agno.com/) - [Open source: partial — SDK and AgentOS are Apache 2.0; the control plane is the commercial part and is not published as source.](https://www.agno.com/compare/agno-vs-langgraph) [View Agno](https://theagentsindex.com/agno) ### 3. Cursor Coding agent in a desktop editor, terminal CLI, cloud VMs and CI, priced per seat plus token usage. **Research coverage:** 35/35 criteria **Where it improves on Letta:** - [Writes tests: yes — Test generation is named as agent work, and Automations can be configured to add tests on every new commit.](https://cursor.com/automate) - [Whole-codebase work: yes — Cloud agents work across multiple repositories in one task and raise a pull request in each repo they touch.](https://cursor.com/docs/cloud-agent) - [MCP server: partial — MCP is inbound only: Cursor is the client that connects to MCP servers. Another agent drives Cursor over ACP (agent acp) or the SDKs, not by querying an MCP endpoint Cursor exposes.](https://cursor.com/docs/mcp) **Trade-offs against Letta:** - [Open models: partial — All inference is hosted: the catalogue includes GLM 5.2 from Z.ai and Kimi K3 from Moonshot, but there is no path to point Cursor at open weights you run.](https://cursor.com/docs/models-and-pricing) - [Self-hosted: partial — Only tool execution moves to your machines: Cursor still runs the agent loop, inference and planning, and the Self-Hosted Pool needs Enterprise. The Enterprise FAQ says there is no on-premises deployment.](https://cursor.com/docs/cloud-agent/self-hosted) - [Open source: no — The Terms of Service forbid deriving or accessing the source; the /licenses page covers only third-party open source components used inside the IDE.](https://cursor.com/terms-of-service) [View Cursor](https://theagentsindex.com/cursor) ### 4. Junie JetBrains coding agent for the terminal, JetBrains IDEs and CI, running on hosted or your own model keys. **Research coverage:** 35/35 criteria **Where it improves on Letta:** - [Writes tests: yes — Test generation is documented as a first-class task rather than a side effect of writing code, driven through the portable agent-skills mechanism so output follows the project's existing test style.](https://junie.jetbrains.com/docs/agent-skills.html) - [Whole-codebase work: yes — The vendor claims repository-wide edits rather than single-file assistance, and markets long-running migrations specifically as the case its asynchronous remote mode exists for.](https://www.jetbrains.com/help/ai-assistant/junie-agent.html) - [MCP server: partial — MCP runs one way only: Junie consumes external MCP servers as a client. Another program reaches it through ACP instead, and no MCP server exposing Junie is documented.](https://junie.jetbrains.com/docs/junie-cli-acp.html) **Trade-offs against Letta:** - [In a browser: partial — The web app is a companion view onto a CLI session still running on your own machine, not a standalone hosted agent, and the vendor lists a dozen features it cannot do.](https://junie.jetbrains.com/docs/junie-cli-remote-mode.html) - [Self-hosted: partial — The agent binary always runs on your machine and models can be local, but running the surrounding JetBrains AI service on your own infrastructure is ticked for AI Enterprise alone.](https://www.jetbrains.com/ai-ides/buy/) - [Open source: no — The public repository carries installers, model profiles and a plugin rather than agent source, and its licence section reserves all rights and points at proprietary service terms.](https://github.com/JetBrains/junie) [View Junie](https://theagentsindex.com/junie) ### 5. Codex CLI OpenAI's terminal coding agent for inspecting, editing and running repository code from the shell. **Research coverage:** 35/35 criteria **Where it improves on Letta:** - [Writes tests: yes — Documented CLI workflow for writing a unit test for a named function.](https://learn.chatgpt.com/docs/prompting) - [MCP server: partial — Codex is an MCP client for local and remote servers, but exposing Codex itself as an MCP server is deprecated in favour of the app server.](https://learn.chatgpt.com/docs/codex-sdk) - [Seat model: yes — Per-user pricing with a two-seat floor and no published ceiling; monthly billing costs $25 per user.](https://learn.chatgpt.com/docs/pricing) **Trade-offs against Letta:** - [Claude: no — Sign-in and model support are OpenAI models only; no Anthropic model appears in any documented model list.](https://learn.chatgpt.com/docs/auth) - [Model choice: partial — You pick the model per run and can define custom providers, but the first-party catalogue is OpenAI models only.](https://learn.chatgpt.com/docs/config-file/config-advanced) - [Self-hosted: partial — The agent binary runs on your machine or runner; inference is OpenAI-hosted unless you route it through your own AWS Bedrock account.](https://learn.chatgpt.com/docs/amazon-bedrock) [View Codex CLI](https://theagentsindex.com/codex-cli) ### 6. Factory Droid coding agents that run in the desktop app, CLI, IDEs, CI and Factory-managed cloud computers. **Research coverage:** 35/35 criteria **Where it improves on Letta:** - [Writes tests: yes — The /install-qa skill generates QA sub-skills and executes end-to-end test flows per diff, with evidence.](https://docs.factory.ai/software-factory/automated-qa) - [Whole-codebase work: yes — Missions decompose multi-feature work into milestones and are documented for brownfield migrations.](https://docs.factory.ai/missions/overview) - [MCP server: partial — Droid is an MCP client over stdio/http/sse and can be driven by another program over JSON-RPC or ACP, but no Factory-hosted MCP server is documented.](https://docs.factory.ai/harness/mcp) **Trade-offs against Letta:** - [Self-hosted: partial — The agent always runs on your machine, and a dedicated airgap build exists, but airgap builds are Enterprise-only and not publicly distributed.](https://docs.factory.ai/enterprise/airgapped-deployment) - [Open source: partial — The CI action is a public repository; the Droid agent itself ships as binaries, with no source offered.](https://docs.factory.ai/software-factory/code-review-ci) - [Free tier: no — The published plan list starts at Pro $20/mo; no free tier or trial is offered, though Droid Core and a BYOK allowance are free within a paid plan.](https://docs.factory.ai/pricing/individuals) [View Factory](https://theagentsindex.com/factory-ai) ## Method Unknown data is never treated as a benefit or a trade-off. Featured placement is labelled but cannot alter recommendation order.