AXLR vs Kiro CLI

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.

Kiro CLI 40

Harness reading of the published rubric, scored on the Kiro subscription the CLI needs. No payment protocol (0). Plan prices, the $0.04 credit price and per-model credit multipliers are public without a login (20). Kiro Free has 50 credits a month, and the pricing page asks for a card only on upgrade (20). A person signs in through a browser or device flow, and the API key for headless runs is created by hand at app.kiro.dev on a paid plan (0).

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.

Kiro CLI 67

Framework reading, adapted to a harness driven by a pipeline. --trust-tools limits approved tools, disabledTools removes MCP tools per server, tool search loads MCP tools on demand, and custom agents carry their own tool set (20). Compaction and a workflow timeout (KIRO_HEADLESS_WORKFLOW_TIMEOUT_SECS, six hours by default) exist, but no cap on turns or run time for a plain headless run was found (10). Distinct exit codes for MCP startup failure and a missing agent, --require-mcp-startup, and a final interruption record in stream-json, with exit 1 for everything else (14). Sessions are saved every turn, with --resume, --resume-id and checkpoints with rewind (15). No SDK. The programmatic interfaces are the headless command and the ACP server, and a headless run needs a paid-plan API key and explicit trust flags (8).

AXLR 55

Apache-2.0 with a NOTICE (30). No privacy policy or terms on underpassai.com or axlr.underpassai.com; the docs' 'Where data goes' and 'Diagnostics and privacy' sections say that model requests go to OpenRouter, the local server or the native API, that Jev sends text to TypeSafe only when on, that sessions live under $XDG_STATE_HOME/axlr, that payload capture is off by default and redacted when on, and that traces are deleted after 30 days; nothing covers the engine downloads' or the catalog registry's handling of a client's requests (15). No deprecation policy; pre-1.0 changes are dated inline in the docs and the product contract records the 5 October 2026 retirement of the first skill catalogue after the fact (6). No telemetry to disclose, and the docs say in two places what leaves the machine and how to stop payload capture, though no single page says there is no telemetry (17). 30+15+6+17 = 68.

Kiro CLI 71

Proprietary, with clear terms. The licence page puts the CLI under the AWS Customer Agreement and the AWS Intellectual Property Licence, where the Amazon Q Developer CLI it replaced was Apache 2.0 (15). The data protection page says what is stored for Free, individual and enterprise users, names US East (N. Virginia) for storage, lists inference regions, and gives 60 days for Free Tier abuse detection and 30 days for some models. It agrees with sections 50.3 and 50.14 of the AWS Service Terms. No general retention period for stored content was found, per the 8 October check (22). The models page has a model lifecycle section (page updated 17 October 2026) with Experimental, Active and EOL stages, says Kiro generally schedules model end of life alongside Amazon Bedrock and shows the date in the model picker, and lists Claude Sonnet 4.0 as ending on 14 October 2026. 2.30.0 says V3 becomes the default with CLI 3.0 at the end of October, Classic sessions carry a deprecation notice, and V3 has a breaking-change table and migration guides. No minimum notice period is stated, and we found no notice of the Sonnet 4 date before the 14 October changelog entry (14). Telemetry types are listed and telemetry.enabled turns them off, with collection on by default (15). 15+22+14+15 = 66.

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.

Kiro CLI 57

Local-package reading, the same as the other closed-source harnesses. An install script that verifies SHA-256 checksums, a .deb, an AppImage and a PowerShell script, with macOS, Windows 11 and Linux (glibc 2.34 or newer, or musl) stated (20). No public CI or test suite, since the source isn't published and the GitHub repository is an issue tracker (0). Per the 8 October check, not re-read on 17 October, 1,401 open issues in the shared Kiro tracker, 428 labelled cli, with 96 cli issues opened and 69 closed in the 30 days to 8 October, area labels, a triage label and stale-issue automation. Open reports from the week to 8 October included a --no-interactive run that never exits after a refusal (12). A dated changelog for every release and a breaking-change table with a migration guide for V3, which runs beside 2.x until the user opts in, though 2.24.0 stopped loading project .env files in a minor version (10). 2.31.1 is the released line, with V3 still an early release that 2.30.0 says becomes the default with CLI 3.0 at the end of October (15). 20+0+12+10+15 = 57.

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.

Kiro CLI 69

Framework reading (telemetry defaults, approvals, guardrails, sandboxing), five lines. Telemetry and content collection are on by default for Free and individual accounts, each with a documented opt-out, and enterprise users are opted out. API keys are long-lived and revocable with no scopes, and administrators must switch key generation on (14). Deny over ask over allow across six scopes, hard-coded denies on Kiro's own settings paths, workspace trust and a managed policy that fails closed. Since 2.31.0 (13 October 2026) every V3 user can run /sandbox to put agent shell commands and local stdio MCP servers in an operating-system sandbox, with outbound network blocked, limited or open, and /autonomous on turns it on first. It is off unless chosen, it doesn't cover the agent, built-in file tools or remote MCP servers, V3 is still an early release beside 2.x, and AWS says managed policies are client-enforced and can be circumvented (17). An untrusted workspace doesn't load its agents, steering, MCP configuration or skills, and can read but not write memories. Compound shell commands are split before matching, and the MCP page warns that servers run outside any sandbox (11). Enterprise prompt logging to the customer's S3 bucket covers the CLI, with daily activity reports and OpenTelemetry export, and individuals have local logs only (11). AWS vulnerability reporting through a HackerOne disclosure programme with no paid bounty, CVEs published in security bulletins with credit to reporters, ISO/IEC 27001:2022 scope and HIPAA eligibility. The aws.amazon.com security.txt is valid again (Expires 2027-10-16), which is the 17 October reading for every AWS listing, and kiro.dev/.well-known/security.txt still answers 404, so 2 are held back for that and 2 for no bounty (16). 14+17+11+11+16 = 69.

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.

Kiro CLI 73

2.31.1 on 14 October 2026 (30). At least 12 minor versions (2.20.0 on 26 August to 2.31.0 on 13 October) and their patches (20). A public issue tracker with area labels and triage automation, 69 cli issues closed against 96 opened in the 30 days to 8 October, and a Discord server, per the 8 October check, not re-read on 17 October. We didn't establish how many replies come from staff (14). No SDK and no registry entry. The ACP server is kept current, with a migration guide for clients moving to V3 (6). Closed source, so no CI or dependency health to read. The installer verifies checksums (3). 30+20+14+6+3 = 73.