Head to head · Multi-agent orchestration · October 2026 research run

AXLR vs Paperclip

AXLR scores 70.6 (BB) on agent readiness against Paperclip's 59 (C), and leads in 3 of 7 scored categories. Paperclip leads on transparency & trust. Both do multi-agent orchestration.

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 70

Also in its favour

  • Agent-ready, a grade of BB or better
  • No incidents deducted, where Paperclip loses 10 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

Paperclip C

Best for Someone running several coding or operations agents who wants one place for tasks, budgets, approvals and history across harnesses.

Ahead on

  • Transparency & trust, 66 against 55

Watch for

claude_local defaults dangerouslySkipPermissions to true and codex_local defaults to bypassing approvals and the sandbox, with agents running on the host

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.

Agent ergonomics AXLR +13

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.

Paperclip 70

Harness reading of the framework line, scored on what an agent or pipeline driving it has to supply. The MCP server lists 44 tools with no toolsets or read-only subset found, offset by compact reads such as paperclipInboxLite and the heartbeat context (12). Budgets by company, agent and project with an automatic pause at 100 per cent, though the README says enforcement uses recorded spend and can lag work in flight (16). onboard --yes, CLI commands with --json, the REST API and routines started by cron, webhook or API (16). Atomic task checkout with a documented 409, Idempotency-Key on routine triggers, saved sessions and bounded recovery (17). One command starts a server with embedded PostgreSQL, but it needs Node.js 24.11 and each harness CLI installed and signed in on the host, and we found no client SDK beyond the TypeScript plugin SDK (9).

Transparency & trust Paperclip +11

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.

Paperclip 66

MIT (30). The privacy policy of 23 July 2026 separates self-hosted use from the hosted services and names Paperclip Labs, Inc., but keeps data as long as reasonably necessary, lists no subprocessors, and the 90-day telemetry retention appears only in source. The terms grant a broad licence over content sent to the services and allow model training on opt-in detailed telemetry (16). Release notes carry dated Breaking Changes sections and upgrade guides, with no written deprecation policy or notice period (10). The README discloses telemetry, what it excludes and four opt-outs, and the event contract is public in the repository, but it is on by default (17).

Score by category

CategoryWeight this runAXLRPaperclipEdge
Reliability16%207066AXLR +4
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28081Paperclip +1
Agent ergonomics13%16.28370AXLR +13
Security & auth14%17.56264Paperclip +2
Payments & pricing10%12.56060even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87978AXLR +1
Transparency & trust7%8.85566Paperclip +11
Negative events≤150-10
TotalBB 70.6/100C 59/100

Facts side by side

FactAXLRPaperclip
KindAgent harnessAgent harness
VendorUnderpass AIPaperclip Labs, Inc.
Hosted endpointno (local only)no (local only)
Transports
AuthOAuth or keyOAuth or key
PricingFreeFree
x402nono
LicenceApache-2.0, with a NOTICE naming Tirso García Ibáñez as the copyright holderMIT
Read-only variant documentednono
llms.txtnoyes
Last release2026-10-252026-10-05
Terms last updatedno document linked2026-07-23
Privacy policy last updatedno document linked2026-07-23
Customer content may train modelsnot read yetyes, with an opt-out
Terms restrict automated accessnot read yetnot found in the text
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 stars99k stars, 60k npm/wk

How the scores have moved

AXLR

No score change since it was listed.

Paperclip

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.

Paperclip

Board approvals, budgets with a hard stop and an activity log sit above whichever harnesses do the work, and eleven stable versions shipped in 90 days. The Claude Code and Codex adapters skip permission prompts and the sandbox by default, and twelve security advisories, five of them critical, have been published since April 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

Paperclip

  1. Set PAPERCLIP_TELEMETRY_DISABLED=1 or DO_NOT_TRACK=1 before the first start. Telemetry is on by default
  2. Set dangerouslySkipPermissions and dangerouslyBypassApprovalsAndSandbox to false on agents that read untrusted input, or run them in a sandbox provider
  3. Install with Node.js 24.11 or newer, and install and sign in to each harness CLI on the host first. Paperclip assumes they are there
  4. Use --bind lan or --bind tailnet at onboarding for anything beyond one machine. The default local_trusted mode treats every request as the board admin
  5. Treat 409 on task checkout as owned by another agent and pick different work. The API docs say not to retry

Questions

Which is better for AI agents, AXLR or Paperclip?

AXLR scores 70.6 (BB) on agent readiness against Paperclip's 59 (C), and leads in 3 of 7 scored categories. Paperclip leads on transparency & trust.

Are AXLR and Paperclip open source?

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

Other comparisons with AXLR or Paperclip

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.