Letta vs Rovo Dev CLI

Letta 60

No x402, MPP or L402 (0 of 40). Per-unit API prices are public, $0.10 per active agent a month and $0.00015 a second of tool execution, plus plan prices (20). A $0 plan with bring-your-own keys; no card is mentioned (20). The CLI runs locally without signing in (20). Total 60.

Rovo Dev CLI 15

Harness reading of the published rubric, scored on the Rovo Dev subscription the CLI needs. No payment protocol (0). Rovo Dev Standard is $20 a developer a month with 2,000 credits and extra credits are $0.01, both public. The credit multiplier for each model is shown only inside the CLI, and a task is given only as a range (5 to 50 tasks per 2,000 credits), so a run's cost can't be worked out before signing up. Judgement call between the 10 for plan-only pricing and the full 20 (15). Rovo Dev Free gives 350 credits a month, but only on Jira Standard or Premium sites, which are paid plans, and the 30-day Standard trial excludes the CLI (0). An organisation admin activates Rovo Dev and the user creates an API token in a browser (0). 0+15+0+0 = 15.

Letta 70

Harness reading. docs.letta.com serves llms.txt and a Markdown version of every page, with an applies_to block saying which backend and interface each page covers (10). TypeScript types for the Agent SDK and a documented App Server WebSocket protocol, but no JSON Schema or OpenAPI for the harness (15 of 25). Pages say when to use local or cloud backends, subagents and channels (14 of 20). Permission modes and options are typed in the SDK (12 of 15). Example applications and a remote client reference (11 of 15). Releases most days but no changelog file (8 of 15). Total 70.

Rovo Dev CLI 45

Framework reading. Server mode lists its /v3 endpoints with request bodies, and an Atlassian engineering post of 27 October 2025 says Swagger docs are served at localhost:<port>/docs. That contract is only visible on a running server, and no schema for the SSE events or the config file was published (12). No llms.txt on support.atlassian.com or developer.atlassian.com, and no Markdown twins found (0). The tools page says what allow, ask and deny do, what YOLO mode skips and that MCP tools keep their permissions, and the settings page gives each default. Little says when not to use a mode (12). Permission levels, console output formats and tool names are enumerated in the settings reference with defaults (10). Server mode has curl, Python and JavaScript examples. No exit codes or error responses are documented beyond the post's note that a failed entitlement check disables every endpoint except healthcheck and shutdown (7). The API path is versioned (/v3), but there is no public changelog for Rovo Dev builds (4). 12+0+12+10+7+4 = 45.

Letta 85

v0.34.42 on 6 November 2026 (30). Dozens of releases in 90 days (20). Pull requests are merged daily; recent issues from users have few replies (15 of 25). npm and PyPI packages and the Agent SDK track the releases (12 of 15). Lock files, CI and nightly smoke tests (8 of 10). Total 85.

Rovo Dev CLI 61

Atlassian's AtlasCode extension, which downloads the same Rovo Dev binary for the IDE, pinned build 202610.16.1b1 in its pre-release of 16 October 2026, and the Atlassian CLI repository served 1.3.39-stable on 23 September 2026. We didn't run the CLI to read the version it installs. Judgement call (30). AtlasCode pinned eight Rovo Dev builds between 23 July and 16 October 2026 (20). No public changelog for the builds. Support is through Atlassian Support and the community, where the Rovo Dev board was last active on 16 January 2026 (5). No SDK and no registry entry. The server-mode API is kept current for the IDE extension (3). The Homebrew formula carries checksums and the Linux repositories are signed. There's no public CI (3). 30+20+5+3+3 = 61.

Letta 58

Local-software lines, read for the harness. @letta-ai/letta-code on npm with Node.js 22.19 or newer, and PyPI wheels for glibc Linux, macOS 14 and Windows x64 with Python 3.9 or newer stated (20). ci.yml, nightly update smoke tests and Telegram live smoke tests exist, but GitHub's API answered with a rate limit, so run results were unread (15 of 25, unchecked). 332 open issues and pull requests, mostly pull requests; recent bug reports such as recall reading the wrong conversation have no reply yet (15 of 25). 398 tags at 0.34.x with release notes on GitHub, no changelog file, and breaking removals such as AgentFile announced in the README (8 of 15). Pre-1.0 (0). Total 58.

Rovo Dev CLI 35

Local-package reading, the same as the other closed-source harnesses. Rovo Dev ships inside the Atlassian CLI, which installs from a Homebrew tap with SHA-256 checksums, signed apt and yum repositories and curl downloads for macOS, Linux and Windows on amd64 and arm64, and Rovo Dev downloads itself on first use (20). No public CI or test suite, since the source isn't published (0). No public issue tracker. The Rovo Dev community board was last active on 16 January 2026, and bugs otherwise go to /feedback and Atlassian Support, so open crash reports can't be counted (8). Rovo Dev builds moved from 0.13.x to date-based versions such as 202604.30.2 and 202610.16.1b1, per AtlasCode's changelog and manifest, and have no public changelog, and the Atlassian CLI changelog stops at v1.3.15 while its repository serves 1.3.39 (2). Rovo Dev has been rolling out as a product since October 2025, but the version number carries no stability signal and Atlassian has announced that the standalone product will reach end of life. Judgement call (5). The CLI runs against Atlassian's hosted service, and the Rovo status page has no Rovo Dev component. 20+0+8+2+5 = 35.

Letta 67

Harness reading. Toolsets switch with /model, skills load per agent, and subagents run in the background (18 of 25). Context is managed through memory blocks, reflection and dreaming (12 of 20). letta -p --output-format json for scripted runs and an App Server for programmatic control (12 of 20). Conversations resume by agent and conversation id, and memory is git-tracked so changes can be reverted (15 of 20). Runs with no account on the local backend, with one SDK language, TypeScript (10 of 15). Total 67.

Rovo Dev CLI 53

Framework reading, adapted to a harness driven by a pipeline. Per-tool allow, ask and deny, allowedMcpServers and disabledMcpServers, tool lists on subagents and skills, and /prune to drop tool results from context (15). The console output format is markdown, simple or raw. No JSON output for acli rovodev run is documented, server mode streams JSON events, and no turn or spend cap exists beyond the credit allowance and /efficiency (10). No exit codes are documented. Server mode reports entitlement and credit failures, per the engineering post (6). Sessions persist with --restore, fork and rename. --worktree isolates a run with a lock and keeps the worktree when a non-interactive run leaves changes, and server mode has cancel and reset (15). Sensible defaults, but no SDK, and a run needs an API token, a Rovo Dev licence and an activated site (7). 15+10+6+15+7 = 53.

Letta 35

Harness reading of the framework checklist, as for the other harnesses. 30 for what leaves the machine by default, 20 for approvals and sandboxing, 15 for injection posture, 15 for audit and 20 for the security programme. Letta Cloud is the default backend, so agent state and conversations go to Letta's servers, and telemetry is on by default (10 of 30). The default permission mode is unrestricted; standard, acceptEdits and strict are opt-in, and cloud sandboxes exist for remote work (4 of 20). No prompt-injection guidance found for fetched pages or channel messages (5 of 15). Conversation search and git history of memory give an operator a record of what the agent saw and changed (10 of 15). SECURITY.md routes reports to support@letta.com and scopes out the retired server; no security.txt, bounty or certification found (6 of 20). Total 35.

Rovo Dev CLI 48

Harness reading of the framework checklist, as for the other harnesses. 30 for credentials and what leaves the machine, 20 for approvals and sandboxing, 15 for prompt-injection posture, 15 for audit and 20 for the security programme. The CLI processes data on the device and sends prompts to Atlassian's models, whose providers don't retain or train on them, per the Rovo privacy page and the AI Terms. The scoped token the docs create carries about 50 scopes including write, delete and admin:repository:bitbucket, the pipelines guide asks for an unscoped token, and no telemetry description for the CLI was found (12). Writes and shell commands ask by default, reads are allowed, bash rules are regex, compound commands are split and file access stays in the workspace. There is no sandbox for customers (runInSandbox is macOS only and for internal users), --yolo skips file and shell prompts, and project-level skills in a cloned repository can list pre-approved tools. We found no workspace trust step (10). MCP server instructions go into the system prompt by default, with a per-server enable_instructions switch, and the MCP page says data isn't sent to third-party tools without the user's approval (7). Administrators can turn Rovo Dev on and off per organisation and site and see credit use. Logs stay local in ~/.rovodev/logs, and no audit log of CLI actions was found (5). security.txt is valid (Expires 2027-02-04), Atlassian runs a public Bugcrowd bug bounty and publishes its fix objectives. The rollout page says Rovo Dev hasn't been externally audited for ISO 27001 or SOC 2, and we didn't check whether the bounty scope names Rovo Dev (14). 12+10+7+5+14 = 48.