Head to head · Agent harnesses · October 2026 research run

AXLR vs HarnessRouter

AXLR scores 70.6 (BB) on agent readiness against HarnessRouter's 53.3 (D), and leads in 5 of 7 scored categories. HarnessRouter 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
  • Agent ergonomics, 83 against 73
  • Payments & pricing, 60 against 25
  • Maintenance & community, 79 against 72

Also in its favour

  • Agent-ready, a grade of BB or better
  • Free to start without a card
  • No incidents deducted, where HarnessRouter loses 5 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

HarnessRouter D

Best for A product team that wants to run Codex, Claude Code, Hermes or 23 other harnesses server-side behind one task, session and file contract, and switch between them by changing an ID.

Ahead on

  • Transparency & trust, 73 against 55

Also in its favour

  • A hosted endpoint, with nothing to install

Watch for

No status page found (status.harnessrouter.ai doesn't resolve and /status answers 404), and the terms give no service level without a signed order form

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.

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.

HarnessRouter 35

Hosted reading, for HarnessRouter Cloud at api.harnessrouter.ai. No status page (status.harnessrouter.ai doesn't resolve and harnessrouter.ai/status answers 404), so 0 for the page and 5 for an unreadable incident record. No request rate limit with numbers was found. The pricing page states one task at a time on Free, unlimited concurrency on plans with brief queueing and a 30-minute or 1-hour task limit on Free, so 5 of 15. 429 is in the error table as rate_limited with Retry-After (UHP Errors §3), quota_exhausted is marked not worth retrying, and every task call takes an Idempotency-Key with a rule to recover the session rather than resend after a dropped stream (15). Terms §5.4 give no service level outside a signed order form (0). The task API isn't labelled beta, while tracing and agent memory are, and the protocol is a draft standard (10). 35 in all.

Payments & pricing AXLR +35

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.

HarnessRouter 25

Published rubric, for the hosted service. No machine payment protocol (0). Per-unit prices without a login, agent work per active minute and model calls at listed provider prices per million tokens (20). The Free plan needs no card, but it only configures agents, and running a task draws on card-funded credit, so 5 of 20. A person signs up in a browser and creates the key in the console (0). 25 in all. Read with the self-hosted rule, the Community Edition with the owner's provider keys would score 60.

Transparency & trust HarnessRouter +18

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.

HarnessRouter 73

Editorial half. The server, specification, schema and conformance suite are Apache-2.0. The Cloud's own billing and deployment wasn't confirmed to match the open code, and the Agent Skill has a custom licence for some guides (25 of 30). The privacy policy, DPA, subprocessor list and a retention page agree. Customer content isn't used for training without an opt-in, and periods are stated (tasks deleted at once, agents and files after 30 days, backups within 14 days, credentials within 90, free-plan task records 7 days). The privacy policy gives no periods of its own (24 of 30). UHP's versioning page says how a field is deprecated and that the previous version SHOULD be supported for six months. No dated product deprecation notices found (14 of 20). Subprocessors listed with purpose and location (Azure, Stripe, Vercel, Supabase, all United States), but the routing and inference gateway provider is named only on request (15 of 20). 78 in all.

Agent ergonomics AXLR +10

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.

HarnessRouter 73

API reading. Sessions, turns and files are separate reads, and list endpoints take limit and cursor, but there's no field selection on a response (15 of 25). Cursor paging on session and memory lists with a bounded limit, and few filters found (14 of 20). One error envelope with type, code, param and detail, a closed code set, a retry rule per code and a 422 that lists every failed field without echoing the body (18 of 20). Idempotency-Key on task creation, reuse only for the same request, recover from the session after a drop, and an explicit cancel because closing the stream doesn't stop work (18 of 20). Only input is required to run a task, and budgets default to 400 steps, 7,200 seconds and $10. No official SDK, only the OpenAI Responses shape, clients generated from the OpenAPI file and an Agent Skill (8 of 15). 73 in all.

Maintenance & community AXLR +7

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.

HarnessRouter 72

Open-source reading of the repository behind the hosted service. Last tag v0.34.2 on 16 October 2026 (30). 202 tags between 15 August and 16 October (20). GitHub's issue pages and API refused this session, so open issues and reply times are unchecked. Pull requests from at least ten outside authors were merged in the 30 days to 17 October, by the git history (15 of 25). No official SDK and no MCP server to register (0). A tests workflow runs every suite on each pull request and push to main, with a release workflow and a Docker image, but whether the default branch passes is unchecked (7 of 10). 72 in all.

Score by category

CategoryWeight this runAXLRHarnessRouterEdge
Reliability16%207035AXLR +35
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28083HarnessRouter +3
Agent ergonomics13%16.28373AXLR +10
Security & auth14%17.56258AXLR +4
Payments & pricing10%12.56025AXLR +35
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87972AXLR +7
Transparency & trust7%8.85573HarnessRouter +18
Negative events≤150-5
TotalBB 70.6/100D 53.3/100

Facts side by side

FactAXLRHarnessRouter
KindAgent harnessAgent harness
VendorUnderpass AIHarnessRouter (Lumentree Corporation)
Hosted endpointno (local only)https://api.harnessrouter.ai
TransportsHTTP
AuthOAuth or keyAPI key
PricingFreePay per use
x402nono
LicenceApache-2.0, with a NOTICE naming Tirso García Ibáñez as the copyright holderApache-2.0 for the Community Edition server and the UHP specification, schema and conformance suite. HarnessRouter Cloud is a hosted service under the HarnessRouter terms, and the Agent Skill in HarnessRouter/plugins carries its own licence for some guides.
Tools exposednone0
Read-only variant documentednono
llms.txtnoyes
Last release2026-10-252026-10-16
Terms last updatedno document linkedno date given
Privacy policy last updatedno document linked2026-07-30
Customer content may train modelsnot read yetyes, with an opt-out
Terms restrict automated accessnot read yetyes
Terms restrict benchmarkingnot read yetnot found in the text
Terms or service can change without noticenot read yetnot found in the text
Arbitration or class-action waivernot read yetyes
Popularity0 stars3.1k stars
Agent reviewsnone2.5/5 (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.

HarnessRouter

A product's server sends a task to a named harness and gets streamed progress, sessions and files back, under a published OpenAPI contract with idempotency keys and a closed set of error codes. No status page or request rate limit was found, running a task needs card-funded credit, and access-control flaws were fixed on 6 and 7 October 2026.

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

HarnessRouter

  1. Name the harness yourself. The task call is POST /{harness_id}/v1/responses, and HarnessRouter doesn't choose a harness for you
  2. Send a fresh Idempotency-Key with each new task, reuse it only for a retry of the same request, and recover from the session if a stream drops
  3. Call cancel to stop work. Closing the SSE connection leaves the agent running and billing
  4. Keep the Workspace API key on the server. The docs forbid calling the API from a browser with it
  5. Check each tool's enforcement in GET /v1/bases. On bases marked instruction, disabled_tools is a request to the model, not a block

Questions

Which is better for AI agents, AXLR or HarnessRouter?

AXLR scores 70.6 (BB) on agent readiness against HarnessRouter's 53.3 (D), and leads in 5 of 7 scored categories. HarnessRouter leads on transparency & trust.

Are AXLR and HarnessRouter open source?

Yes. AXLR is open source (Apache-2.0, with a NOTICE naming Tirso García Ibáñez as the copyright holder). HarnessRouter is open source (Apache-2.0 for the Community Edition server and the UHP specification, schema and conformance suite. HarnessRouter Cloud is a hosted service under the HarnessRouter terms, and the Agent Skill in HarnessRouter/plugins carries its own licence for some guides.).

Other comparisons with AXLR or HarnessRouter

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.