# Alternatives to zot > Source: https://theagentsindex.com/zot/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. goose Open source AI agent for coding and general tasks; runs locally as a desktop app, CLI, or ACP server. **Research coverage:** 34/35 criteria **Where it improves on zot:** - [Debugs and fixes: yes — The docs describe the full loop of reading the failure, finding the root cause, changing code and verifying, not just a suggested patch.](https://goose-docs.ai/docs/guides/sessions/smart-context-management) - [Writes tests: yes — Writing new tests is described as goose's own output, alongside spotting the gaps in existing coverage.](https://goose-docs.ai/docs/mcp/repomix-mcp) - [Reviews code: yes — A first-class CLI verb reviews a diff you did not write, and it picks up repo-local review checks from .agents/checks/*.md.](https://goose-docs.ai/docs/guides/goose-cli-commands) **Trade-offs against zot:** - No researched regression against the baseline. [View goose](https://theagentsindex.com/goose) ### 2. OpenHands Open-source software engineering agent with a browser client, CLI and Python SDK; local, cloud or self-hosted. **Research coverage:** 34/35 criteria **Where it improves on zot:** - [Debugs and fixes: yes — Investigates failing builds, tests and production errors and can implement the fix, not just describe it.](https://www.openhands.dev/services) - [Writes tests: yes — Test generation and coverage expansion is a named workflow; a separate QA agent also exercises the running software rather than the test suite.](https://www.openhands.dev/services) - [Reviews code: yes — A GitHub Actions PR-review agent posts inline comments with priority labels on someone else's diff.](https://docs.openhands.dev/openhands/usage/use-cases/code-review) **Trade-offs against zot:** - [Getting out: partial — Account content can be managed, deleted in-product, or deleted on written request; no data-export mechanism and no credit-expiry term is published, and payments are stated to be non-refundable.](https://www.openhands.dev/privacy) [View OpenHands](https://theagentsindex.com/openhands) ### 3. Letta Stateful agent harness, cloud and SDK for agents with persistent, git-versioned memory. **Research coverage:** 35/35 criteria **Where it improves on zot:** - [Debugs and fixes: yes — Vendor states coding agents debug failures and run test suites.](https://docs.letta.com/handbook/index.md) - [Reviews code: yes — Reviews diffs on demand or on every PR via the GitHub action's prompt input.](https://docs.letta.com/platform/github-action/index.md) - [In your editor: yes — The letta-acp adapter runs Letta as a custom agent in Zed, JetBrains IDEs and Obsidian.](https://docs.letta.com/platform/acp/index.md) **Trade-offs against zot:** - [MCP server: no — MCP runs inbound only: Letta sessions consume stdio, HTTP and SSE MCP servers; no Letta MCP server is published.](https://docs.letta.com/agent-sdk/mcp/index.md) - [Audit log: no — No administrative audit log is published; the Enterprise list stops at RBAC, SSO, quotas and dedicated support.](https://docs.letta.com/pricing/index.md) - [Getting out: partial — Memory is git-backed files you can inspect and sync to your own GitHub repo; credit expiry is never stated.](https://docs.letta.com/handbook/index.md) [View Letta](https://theagentsindex.com/letta) ### 4. Junie JetBrains' coding agent: runs in JetBrains IDEs, the terminal and CI, on JetBrains models or your own keys. **Research coverage:** 34/35 criteria **Where it improves on zot:** - [Debugs and fixes: yes — Debug mode drives a live debugger in a connected JetBrains IDE: breakpoints, runtime state, expression evaluation.](https://junie.jetbrains.com/docs/junie-cli.html) - [Writes tests: yes — Runs code and tests as part of a task and verifies the result; plan mode produces an explicit test strategy and test cases.](https://www.jetbrains.com/junie/) - [Reviews code: yes — Dedicated read-only review subagent for local diffs (/review) and for opened or updated GitHub pull requests, with inline comments.](https://junie.jetbrains.com/docs/junie-review-agent.html) **Trade-offs against zot:** - [Self-hosted: partial — Inference can be fully self-hosted (bundled local engine, Ollama/LM Studio/LiteLLM, or a self-hosted proxy); the agent binary itself is JetBrains-distributed.](https://junie.jetbrains.com/docs/custom-proxies.html) - [Open source: no — The official JetBrains/junie repository carries installers and release registries under an all-rights-reserved licence; no agent source is published.](https://raw.githubusercontent.com/JetBrains/junie/main/LICENSE.md) - [API access: partial — Driven programmatically as a headless CLI with a JUNIE_API_KEY token in CI; the published public HTTP API exposes only site metadata and update/registry routes, no task endpoints.](https://junie.jetbrains.com/docs/junie-headless.html) [View Junie](https://theagentsindex.com/junie) ### 5. Juggler Open-source desktop workbench for AI coding agents, with inspectable tool calls and branching threads. **Research coverage:** 30/35 criteria **Where it improves on zot:** - [Debugs and fixes: yes — The documented one-shot example is diagnosing and fixing a failing test.](https://github.com/juggler-ai/juggler/blob/main/docs/headless-linux.md) - [In a browser: partial — A browser UI exists, but it is served by your own machine's server, not hosted by the vendor; WAN reach is only in the official binaries.](https://github.com/juggler-ai/juggler) **Trade-offs against zot:** - [API access: partial — Scriptable through `juggler run --json` (answer, conversation id, turns) rather than a documented HTTP or SDK API for driving sessions.](https://github.com/juggler-ai/juggler/blob/main/docs/headless-linux.md) [View Juggler](https://theagentsindex.com/juggler) ### 6. OpenCode Open source AI coding agent for the terminal, desktop, browser and IDE, running any model you connect. **Research coverage:** 33/35 criteria **Where it improves on zot:** - [Debugs and fixes: yes — Asked to fix an issue, it works in a new branch and submits a PR with the changes.](https://opencode.ai/docs/github) - [Reviews code: yes — Invoked on a review comment it receives the file path, line numbers and diff context, and PR-open events can trigger it automatically.](https://opencode.ai/docs/github) - [In your editor: yes — An extension covers VS Code and its forks, and ACP support puts it inside Zed and JetBrains IDEs.](https://opencode.ai/docs/ide) **Trade-offs against zot:** - [MCP server: no — MCP runs inbound only: external MCP servers become tools inside OpenCode, and no MCP endpoint exposing OpenCode itself is documented.](https://opencode.ai/docs/mcp-servers) - [Getting out: partial — Billing can be switched off at any time and the remaining balance stays spendable.](https://opencode.ai/zen) [View OpenCode](https://theagentsindex.com/opencode) ## Method Unknown data is never treated as a benefit or a trade-off. Featured placement is labelled but cannot alter recommendation order.