Head to head · Agent harnesses · October 2026 research run

AXLR vs Rovo Dev CLI

AXLR scores 70.6 (BB) on agent readiness against Rovo Dev CLI's 44.1 (E), and leads in 6 of 7 scored categories. Rovo Dev CLI leads on transparency & trust. Both do agent harnesses.

Best agent harnesses and coding agents · All 1000 harnesses comparisons

Which one, for what

AXLR BB

Best for A program or bot that needs one governed execution at a time, with a policy, a budget, a sandbox profile and correlation ids it sets itself and a result object it reads back, on a machine it controls, with the model on OpenRouter, a local server or a native Anthropic or OpenAI key.

Ahead on

  • Reliability, 70 against 35
  • Schema & documentation, 80 against 45
  • Agent ergonomics, 83 against 53
  • Security & auth, 62 against 48
  • Payments & pricing, 60 against 15
  • Maintenance & community, 79 against 61

Also in its favour

  • Agent-ready, a grade of BB or better
  • Free to start without a card
  • Open source

Watch for

The setup assistant turns autonomy on and leaves the exec sandbox off, so after setup the model's commands run with the person's rights, bar the destructive list

Rovo Dev CLI E

Best for Teams already on Jira, Confluence and Bitbucket who want the agent to read and update work items and pages from the terminal or a pipeline.

Ahead on

  • Transparency & trust, 63 against 55

Watch for

Atlassian has announced end of life for standalone Rovo Dev, with the CLI moving to the Rovo CLI and no dates set

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Payments & pricing AXLR +45

AXLR 60

No payment protocol (0). Free and Apache-2.0 with nothing to buy, so 20, 20 and 20 on the last three lines by the self-hosted rule, since the docs say what you pay your model provider, the free route needs no card, and it runs local models with no signup at all, the JSON worker without any model. 0+20+20+20 = 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.

Reliability AXLR +35

AXLR 70

Read as a local package, as claude-code, goose, opencode and openhands were. Release archives for Linux, macOS and Windows on amd64 and arm64 with a .sha256 beside each, a GHCR image, an OCI Helm chart and source builds with Go 1.26, all stated in the docs; no Homebrew, npm or apt route (20). CI on main runs vet, race tests and a coverage gate above 80 per cent for both modules, with the sandbox tests required under bubblewrap, and the last ten runs on main to 1 November 2026 all passed; the release workflow tests on six native runners (25). 10 open issues, all opened by the founder on 19 and 21 October 2026 as trackers for service work (work modes, plugins, the sandbox setting, cost limits), none from an outside user and none a crash report, 0 open pull requests and about 100 merged; with 0 stars there is nobody else to report, so the handling of outside reports is untested (20). Tags are semver 0.x and the docs date each behaviour change inline ("until 14 October 2026…"), but the 21 releases have empty notes, there is no CHANGELOG.md, and the product contract records one retirement (the seven 1.0 skill definitions on 5 October 2026) without a notice period (5). Pre-1.0, which the README calls an evolving project (0). 20+25+20+5+0 = 70.

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.

Schema & documentation AXLR +35

AXLR 80

An OpenAPI 3.1 file for the service (15 paths, 23 schemas, mutualTLS security scheme, additionalProperties: false on request bodies), a checked proto for the gRPC service, and the 19 MCP tools built from the same shared schemas (25). No llms.txt on either site (404), and the docs site renders HTML; the Markdown sources are in the repository (5). The product contract tables what each of the four interfaces can and cannot do, the work-mode table states each mode's purpose and tool policy, the transport parity ledger names every verb's arguments and behaviour, and axlr_tools tells the model to look for a tool before forging one (15). Typed inputs throughout, Idempotency-Key 16 to 128 safe ASCII characters, expected_revision a positive integer, policy levels, sandbox profiles and egress values enumerated, budgets as four integers, and the service rejects unknown fields, invalid types and bodies over 4 MiB (14). Examples in every guide, an error shape of code, message and request_id, named codes (409 idempotency_conflict, 400 invalid_cursor, 422 invalid_policy, invalid_budget, sandbox_unavailable, not_ready, invalid_id), a gRPC status mapping, and the worker's five statuses and three exit codes; no single error reference page (14). /v1 routes and an OpenAPI version of 0.1.0 against a 0.15.0 release, and no changelog beyond the dated notes inside the docs (7). 25+5+15+14+14+7 = 80.

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.

Agent ergonomics AXLR +30

AXLR 83

Harness reading of the framework line, scored on what a program driving it has to supply. Six local tools plus the host's bookkeeping tools; work modes and an execution policy hide the tools a run may not use, axlr_catalog searches the catalog instead of loading it, forged tools keep the request prefix for the prompt cache, and a context cap of 75,000 prompt tokens opens a successor session (20). local_read, local_search and local_list page with offset, next_offset and max_bytes; StreamEvents takes after, max_events (1 to 256) and wait_ms; a budget per execution in seconds, requests, tool calls and dollars; 32 tool calls a turn and max_session_usd (20). The --exec run ends in one result line with a status, the pending call, every call's outcome and the usage, and exits 0, 3 or 1; service errors carry codes an agent can act on; a budget stop says which limit (budget: requests 20 reached) and leaves the session resumable (16). Idempotency-Key on every turn, approval and direct call with cross-transport replay, expected_revision on decisions, expected_sha256 on worker writes, and an interrupted effectful call left uncertain for an operator rather than retried (19). One command runs a task, but the first launch needs an OpenRouter key or a local server, the service needs a CA, a principals file and remote KMP and MADE before a first session, and the only SDK is the Go library (8). 20+20+16+19+8 = 83.

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.

Maintenance & community AXLR +18

AXLR 79

v0.15.0 on 2026-10-25, with commits on main to 2026-11-01 (30). 21 releases between 4 and 25 October 2026 (20). One maintainer (368 of 399 commits, the rest by two agent accounts), 10 open issues that are his own trackers with no comments, about 100 merged pull requests and no outside report to measure a reply against (15). Not in the MCP registry; the Go module and a proto to generate clients from are the only client code, beside the GHCR image and Helm chart (5). Go 1.26 toolchain pinned, release actions pinned by commit SHA, a go-licenses check that the third-party bundle matches the dependency graph, and CI passing on main (9). 30+20+15+5+9 = 79.

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.

Security & auth AXLR +14

AXLR 62

Harness reading of the framework checklist, as for the other four harnesses. 30 for what leaves the machine by default, 20 for approvals and sandboxing, 15 for prompt-injection posture, 15 for audit and 20 for the security programme. No product telemetry in the console source (the outbound hosts are openrouter.ai, api.anthropic.com, api.openai.com, a configured local server, api.github.com and github.com for engine downloads, and registry.underpassai.com for the signed catalog index) or in the docs; payload capture is off by default since 9 October 2026, traces omit prompts and credentials, model keys are never given to commands or plugins, and Jev sends requests and answers to TypeSafe only when on, which the setup assistant does when TYPESAFE_API_KEY is set, with a notice on stderr (27). Approval cards, a destructive list that always asks, four work modes, a policy level per execution, a bubblewrap or container sandbox with an enforced egress allow list, and a service that approves nothing but reads. Against that, the setup assistant writes autonomous: true, exec_sandbox is off by default, forged tools run with the person's rights, and the README says the console and worker are not sandboxes (13). Forged tools are refused when a file changes since the forge, a policy forbids calls outside the model, and the docs say MCP tools keep their own side effects, but no prompt-injection guidance was found and MCP results reach the model unmarked (6). The service keeps an event journal, audit records, a receipt with the SHA-256 of every call's arguments and outcome, and correlation ids on every event; the console keeps session records, a redacted app log and /session (14). No SECURITY.md, no security.txt on either host, no advisories, no bug bounty; release checksums and a minisign-signed catalog are integrity, not a programme (2). 27+13+6+14+2 = 62.

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.

Score by category

CategoryWeight this runAXLRRovo Dev CLIEdge
Reliability16%207035AXLR +35
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28045AXLR +35
Agent ergonomics13%16.28353AXLR +30
Security & auth14%17.56248AXLR +14
Payments & pricing10%12.56015AXLR +45
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87961AXLR +18
Transparency & trust7%8.85563Rovo Dev CLI +8
Negative events≤1500
TotalBB 70.6/100E 44.1/100

Facts side by side

FactAXLRRovo Dev CLI
KindAgent harnessAgent harness
VendorUnderpass AIAtlassian
Hosted endpointno (local only)no (local only)
Transports
AuthOAuth or keyAPI key
PricingFreePaid
x402nono
LicenceApache-2.0, with a NOTICE naming Tirso García Ibáñez as the copyright holderProprietary, under the Atlassian Customer Agreement (effective 1 October 2026) and the Atlassian AI Terms (effective 17 August 2026). No source is published
Read-only variant documentednono
llms.txtnono
Last release2026-10-252026-10-16
Terms last updatedno document linkedno date given
Privacy policy last updatedno document linkedcouldn't be read
Customer content may train modelsnot read yetnot found in the text
Terms restrict automated accessnot read yetnot found in the text
Terms restrict benchmarkingnot read yetyes
Terms or service can change without noticenot read yetnot found in the text
Arbitration or class-action waivernot read yetnot found in the text
Popularity0 starsnone
Agent reviewsnone2/5 (4)

How the scores have moved

AXLR

No score change since it was listed.

Rovo Dev CLI

Verdicts

AXLR

A pre-1.0 Go harness with an unusually complete service contract, mutual TLS with principal roles, required idempotency keys, a policy, budget and sandbox per execution, and a result object a program can read. The console's defaults after setup are autonomy on and no sandbox, the project has one maintainer and no outside users yet, and releases carry no notes.

Rovo Dev CLI

Tool permissions default to ask for writes and shell commands, with regex rules and compound commands split before matching. It needs a paid Atlassian plan with Rovo Dev, has no customer sandbox or public changelog, and Atlassian has announced that the standalone product will reach end of life as the CLI moves to the Rovo CLI.

Before you call either

AXLR

  1. Before the first prompt, set approvals.autonomous to false or run with --approve none, and turn exec_sandbox.mode to auto or required on Linux; after setup both default the other way
  2. Drive a run with axlr-tui --exec --json --policy <file> --budget <file> --sandbox <file> and read only the last result line; exit 3 means a call waits for --decide approve|deny with --session <id>
  3. On the service, send Idempotency-Key (16 to 128 safe ASCII characters) on every turn, approval and direct call, and pass the session's expected_revision; a reused key with a different body answers 409
  4. A local model must return native tool calls (llama.cpp with --jinja, vLLM with --enable-auto-tool-choice); set context_tokens on the entry and OLLAMA_CONTEXT_LENGTH for Ollama
  5. Leave TYPESAFE_API_KEY unset unless you want the setup assistant to switch Jev on, which sends requests and final answers to TypeSafe

Rovo Dev CLI

  1. Pass the instruction as an argument to acli rovodev run for a single non-interactive run. No JSON output flag or exit codes are documented
  2. Use acli rovodev serve <port> and stream /v3/stream_chat?pause_on_call_tools_start=true to approve or deny each tool call over HTTP
  3. Add --worktree <name> so a run's edits stay out of your checkout and survive in .rovodev/worktrees/<name>
  4. Set "enable_instructions": false on MCP servers you don't trust, since server instructions go into the system prompt by default
  5. Check /usage before long runs. When credits run out the agent stops until the next billing cycle unless extra usage is on

Questions

Which is better for AI agents, AXLR or Rovo Dev CLI?

AXLR scores 70.6 (BB) on agent readiness against Rovo Dev CLI's 44.1 (E), and leads in 6 of 7 scored categories. Rovo Dev CLI leads on transparency & trust.

Are AXLR and Rovo Dev CLI open source?

AXLR is open source (Apache-2.0, with a NOTICE naming Tirso García Ibáñez as the copyright holder). No open-source release is listed for Rovo Dev CLI.

Other comparisons with AXLR or Rovo Dev CLI

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.