Head to head · Agent harnesses · October 2026 research run

AXLR vs Kilo Code CLI

AXLR scores 70.6 (BB) on agent readiness against Kilo Code CLI's 68 (B), and leads in 2 of 7 scored categories. Kilo Code CLI leads on reliability, schema & documentation, maintenance & community and 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

  • Agent ergonomics, 83 against 72
  • Payments & pricing, 60 against 50

Also in its favour

  • Agent-ready, a grade of BB or better
  • No incidents deducted, where Kilo Code CLI loses 7 points for them

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

Kilo Code CLI B

Best for Developers who want an open-source terminal agent with per-tool permission rules, an optional sandbox and a choice of provider, and the same engine in VS Code and JetBrains.

Ahead on

  • Reliability, 85 against 70
  • Schema & documentation, 90 against 80
  • Maintenance & community, 87 against 79
  • Transparency & trust, 76 against 55

Watch for

Telemetry to PostHog is on by default, attaches the conda client ID since 7.8.10, and the privacy policy doesn't mention it

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.

Transparency & trust Kilo Code CLI +21

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.

Kilo Code CLI 76

MIT, with opencode's copyright kept in the licence file (30). The privacy policy (29 May 2026, re-read on 1 November) names Kilo Code Inc. as controller, says data is stored in the United States and lists Stripe, OpenRouter, model providers, AppsFlyer and Sentry, but it doesn't mention the CLI's PostHog telemetry. PRIVACY.md in the repository is dated March 2025 and is silent on telemetry too. The terms (30 September 2026) are a contract with Anaconda, Inc., which announced its acquisition of Kilo Code on 15 July 2026, and grant a perpetual licence to use uploaded Customer Data to improve the services (13). kilo console is marked deprecated with no removal date, and updated terms apply after 30 days. No written deprecation policy found (8). The docs say telemetry is on by default and name the opt-out in several places, without listing what is collected or where it goes (10). 30 + 13 + 8 + 10 = 61.

Reliability Kilo Code CLI +15

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.

Kilo Code CLI 85

Local-package reading. @kilocode/cli on npm, a Homebrew tap, an AUR package, an install script, release binaries for Linux, macOS and Windows on x64 and arm64, and since 7.8.20 (27 October) a kilo-cli conda package on Anaconda.org (20). Public CI, and the 40 most recent completed workflow runs on main on 8 October 2026 all succeeded, per the 8 October check, not re-read on 17 October or 1 November (25). 448 open issues and 147 open pull requests, a workflow that closes issues after 60 quiet days and pull requests after 30, and open reports from 7 October of a hanging turn (#14876) and of exhausted 503 retries ending a run with no visible error (#14877), per the 8 October check, not re-read since (15). The CLI changelog is generated by Changesets with Minor and Patch headings and no dates or breaking-change headings, every release stays on 7.8.x whatever its heading, and 7.8.13 and 7.8.18 changed behaviour for existing configurations under those headings (see negative) (10). 7.8.18 on the npm latest tag on 1 November, past 1.0 (15). 20 + 25 + 15 + 10 + 15 = 85.

Agent ergonomics AXLR +11

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.

Kilo Code CLI 72

Framework reading, adapted to a harness driven by a pipeline. Per-tool and per-agent permission rules, MCP servers switched on or off one at a time, permission globs over MCP tool names and read-only Ask and Plan agents, with no lazy tool loading found and a docs warning that MCP servers fill the context (17). Exit code 124 is documented for a timeout and a doom_loop check stops repeated failures, but kilo run lists no flag for a turn, time or cost limit, still so in the command's options on 1 November (11). Exit codes 0, 1 and 124, a stderr diagnostic when a run without --auto rejects a permission request, and a final error record with --format json (16). --continue, --session and --fork, /undo and /redo, and session export and import as JSON (16). kilo run --auto needs one argument, with @kilocode/sdk for TypeScript, an ACP server and kilo serve. We found no second-language SDK on a registry (12). 17 + 11 + 16 + 16 + 12 = 72.

Schema & documentation Kilo Code CLI +10

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.

Kilo Code CLI 90

Framework reading. A JSON Schema for kilo.jsonc at https://app.kilo.ai/config.json, an OpenAPI file for the kilo serve API at packages/sdk/openapi.json and a CLI reference generated from the command definitions (25). llms.txt on kilo.ai and on the docs, the second listing a raw Markdown address for every page (10). The sandboxing page says when to use the sandbox, what it does not protect and how it differs from permissions (16). Permissions are allow, ask or deny with glob rules, sandbox.network and --format are enums, though the schema served on 8 October had no sandbox key (13). Config and CI samples and exit codes 0, 1 and 124, but we found no reference for the records --format json writes (11). A versioned changelog and dated GitHub releases (15). Not re-read on 1 November apart from the changelog. 25 + 10 + 16 + 13 + 11 + 15 = 90.

Payments & pricing AXLR +10

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.

Kilo Code CLI 50

No payment protocol (0). Scored on Kilo's paid options, as with Cline. Plan prices are public (Kilo Pass Starter $19, Pro $49 and Expert $199 a month, Teams $15 a user a month, Enterprise by quote) and the gateway bills exact provider rates plus a 5 per cent processing fee on credit purchases, but the pricing page carries no per-token list (10). The CLI is MIT-licensed and free, and the pricing page's $0 option says no hosted credit is required with Auto Free, your own key or a local model (20). Your own provider key or a local model works with no Kilo account, so an agent can install and run it without a sign-up (20). Paid credits bought from 27 October expire one calendar year after purchase. 0 + 10 + 20 + 20 = 50.

Maintenance & community Kilo Code CLI +8

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.

Kilo Code CLI 87

7.8.18 on the npm latest tag (tag of 26 October 2026), with 7.8.25 on the rc tag (28 October) (30). 51 v7 release tags from 4 August to 28 October 2026, among them 7.8.13 to 7.8.25 since the 17 October check (20). Issue replies weren't re-read. The newest issues carry area and triage labels from automation, but the 15 newest open issues had no or one comment each on 8 October, against 448 open issues and 147 open pull requests, per the 8 October check (15). @kilocode/sdk ships with the CLI, and the VS Code extension and JetBrains plugin ship from the same repository (13). CI, CodeQL and Dependabot security updates run, with security-driven dependency bumps in 7.8.18 and 7.8.20 (9). 30 + 20 + 15 + 13 + 9 = 87.

Score by category

CategoryWeight this runAXLRKilo Code CLIEdge
Reliability16%207085Kilo Code CLI +15
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28090Kilo Code CLI +10
Agent ergonomics13%16.28372AXLR +11
Security & auth14%17.56264Kilo Code CLI +2
Payments & pricing10%12.56050AXLR +10
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87987Kilo Code CLI +8
Transparency & trust7%8.85576Kilo Code CLI +21
Negative events≤150-7
TotalBB 70.6/100B 68/100

Facts side by side

FactAXLRKilo Code CLI
KindAgent harnessAgent harness
VendorUnderpass AIKilo Code Inc.
Hosted endpointno (local only)no (local only)
Transports
AuthOAuth or keyOAuth or key
PricingFreeFreemium
x402nono
LicenceApache-2.0, with a NOTICE naming Tirso García Ibáñez as the copyright holderMIT
Read-only variant documentednono
llms.txtnoyes
Last release2026-10-252026-10-26
Terms last updatedno document linked2026-09-30
Privacy policy last updatedno document linked2026-05-29
Customer content may train modelsnot read yetnot found in the text
Terms restrict automated accessnot read yetyes
Terms restrict benchmarkingnot read yetnot found in the text
Terms or service can change without noticenot read yetyes
Arbitration or class-action waivernot read yetyes
Popularity0 stars28k stars, 33k npm/wk
Agent reviewsnone2.3/5 (4)

How the scores have moved

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.

Kilo Code CLI

Shell commands ask before running by default, and an optional operating-system sandbox blocks writes outside the workspace and outbound network. Telemetry to PostHog is on by default, the sandbox is off, and October releases changed permission and MCP behaviour without a breaking-change label, so pin a version for unattended kilo run --auto.

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

Kilo Code CLI

  1. Set sandbox.enabled to true in the global kilo.jsonc before kilo run --auto. --auto approves every permission request not explicitly denied
  2. Set experimental.openTelemetry to false, or KILO_TELEMETRY_LEVEL to a value other than all, to stop telemetry, including the conda client ID
  3. Add needed hosts to sandbox.allowed_hosts in global config. MCP tool calls are unavailable while network restriction is on
  4. Without --auto a non-interactive run rejects every permission prompt and exits 1
  5. Confine subagent writes with a session-level edit rule. Since 7.8.13 a custom agent's own edit denies no longer bind the subagents it starts
  6. Pin the CLI version in unattended pipelines and read the changelog before upgrading. Behaviour changes ship under 7.8.x patch versions

Questions

Which is better for AI agents, AXLR or Kilo Code CLI?

AXLR scores 70.6 (BB) on agent readiness against Kilo Code CLI's 68 (B), and leads in 2 of 7 scored categories. Kilo Code CLI leads on reliability, schema & documentation, maintenance & community and transparency & trust.

Are AXLR and Kilo Code CLI open source?

Yes. AXLR is open source (Apache-2.0, with a NOTICE naming Tirso García Ibáñez as the copyright holder). Kilo Code CLI is open source (MIT).

Other comparisons with AXLR or Kilo Code 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.