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

herdr vs Paperclip

herdr scores 71.1 (BB) on agent readiness against Paperclip's 56.4 (C), and leads in 4 of 7 scored categories. Paperclip leads on security & auth and maintenance & community. Both do multi-agent orchestration.

Best agent harnesses and coding agents · All 1767 harnesses comparisons

Which one, for what

herdr BB

Best for A developer who runs several coding agents in terminals, locally or over SSH, and wants one agent to start, prompt and wait on others.

Ahead on

  • Reliability, 65 against 59
  • Schema & documentation, 91 against 81

Also in its favour

  • Agent-ready, a grade of BB or better
  • No key needed to call it
  • No incidents deducted, where Paperclip loses 15 points for them

Watch for

Version 0.9.5, not yet 1.0, and the last tagged release is 14 October 2026

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

  • Security & auth, 64 against 49
  • Maintenance & community, 78 against 63

Also in its favour

  • Free to start without a card

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.

Security & auth Paperclip +15

herdr 49

Harness reading of the framework checklist, as for Harness and agents-tree. 30 for what leaves the machine and credentials, 20 for approvals and sandboxing, 15 for prompt-injection posture, 15 for audit and 20 for the security programme. No account, no telemetry found in the source, and a socket file set to 0600. Version and manifest checks reach herdr.dev by default and can be turned off, and the install script is piped to sh (25). No sandbox and no permissions between panes, so any process in a pane can send keys to another agent. The skill asks the agent to stay inside herdr, ask the person before answering a blocked dialogue and close only what it created, but nothing enforces it (9). Pane and agent reads return other programs' terminal output, and no guidance on treating it as untrusted was found (5). A server log, but no per-call audit log found (5). No SECURITY.md or disclosure policy in the repository, and herdr.dev serves no security.txt. CI pins actions to commit SHAs and Dependabot is on (5). 25 + 9 + 5 + 5 + 5 = 49.

Paperclip 64

Harness reading of the framework checklist, as used for the other 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. Anonymous usage telemetry is on by default and goes to telemetry.paperclip.ing. The README lists what is excluded and four opt-outs, and Sentry and OpenTelemetry stay off until configured. We found no first-run notice in the CLI source (18). Board approvals for hires and strategy, execution policies and per-action connection permissions, but claude_local defaults dangerouslySkipPermissions to true, codex_local defaults to bypassing approvals and the sandbox, local agents run on the host, sandbox providers are optional plugins and the default local_trusted mode has no login (10). A documented low_trust_review preset contains agents that read untrusted pull requests or tickets. It is opt-in (10). An activity log of mutating actions, run logs, cost events and audited board API keys (14). SECURITY.md with GitHub private reporting and twelve advisories published per the 8 October check, three now with CVEs in OSV. No security.txt, bug bounty or SOC 2 report found (12).

Maintenance & community Paperclip +15

herdr 63

v0.9.5 on 14 October 2026, 35 days before the check, and the last commit on master on 29 October (20). Six releases from 7 September to 14 October 2026 (20). 495 open issues and 26 open pull requests. The 25 newest issues were labelled triaged with a priority within a day of opening. Unsolicited pull requests are closed automatically and a monthly workflow closes stale issues (15). Not an MCP server and no official SDK (0). Cargo.lock, Dependabot and CI on three systems, run results unread (8). 20 + 20 + 15 + 0 + 8 = 63.

Paperclip 78

Version 2026.1023.0, released on 23 October 2026 per its notes and the site banner (30). Ten stable releases from 2026.817.0 (17 August) to 2026.1023.0 in the 90 days to 4 November (20). Per the 8 October check, not re-read on 4 November, 650 pull requests merged in the last 30 days, but 2,849 issues and 3,338 pull requests were open, 1,396 open issues had no comment, and 309 of the 472 still-open issues from the two weeks before had none (8). paperclipai and @paperclipai/mcp-server publish from the same release workflow. We did not check the MCP registry (12). CI on master, a lockfile refresh workflow and signed image attestations (8). 30 + 20 + 8 + 12 + 8 = 78.

Schema & documentation herdr +10

herdr 91

Read as a CLI and socket API. herdr api schema --json prints a JSON Schema for requests, responses, errors and events, also at docs/next/api/herdr-api.schema.json (25). Markdown for agents, with skills/herdr/SKILL.md and distribution/agent-guide.md. https://herdr.dev/llms.txt indexes the 0.9.5 docs as raw source files for agents (10). The skill says when to use herdr and when not to, and the socket docs say which layer to use for which job, but the schema itself carries few descriptions (15). The schema has 49 enums and agent names are constrained by a pattern, while some inputs are free strings (12). Many CLI and JSON examples, a documented error shape with codes such as not_found, agent_blocked and events_lost (14). Versioned docs per release and a changelog (15). 25 + 10 + 15 + 12 + 14 + 15 = 91.

Paperclip 81

The running server publishes OpenAPI at /api/openapi.json and validates requests with Zod, and the MCP server's tools take Zod schemas. No copy of the spec is published on the docs site, and paperclip.ing/openapi.json describes only the website (22). llms.txt at paperclip.ing, and docs pages answer as Markdown at .md (10). An API reference page per resource and task guides, but the MCP tool descriptions are one line each, such as List agents in a company (13). Typed inputs throughout, apart from the paperclipApiRequest tool, which takes any path under /api and a JSON body (12). cURL, JavaScript and Python examples and a status-code table, with one {error} shape and an occasional details field (12). A changelog page for every stable release and release notes in the repository, but the API path carries no version (12).

Reliability herdr +6

herdr 65

Read as local software, as for agents-tree and Harness. Official release binaries for Linux, macOS and Windows x86_64 with an install script, and Homebrew and mise in the README. The Homebrew formula wasn't read (20). .github/workflows/ci.yml runs checks and tests on ubuntu, macOS and Windows for every push and pull request, but run results couldn't be read from this session, so 15, the value this run gives public CI with unread results. 495 issues were open on 18 November 2026. The 25 newest, opened 15 to 18 November, all carry a triaged label and a priority (p1 or p2), several of them bugs, so reports are sorted within a day but many stay open (15). Semver tags and a Keep a Changelog file with Breaking Changes and Removed sections (15). Version 0.9.5, not 1.0, and not declared stable (0). 20 + 15 + 15 + 15 + 0 = 65.

Paperclip 59

Read as local software. Official npm package paperclipai (Node.js 24.11 or newer) and a Docker image on GHCR (20). Public CI that runs the tests (pr-trusted.yml selects and runs the test shards, and e2e.yml runs the end-to-end suite), with the pass state on master unreadable on 4 November 2026 because GitHub's pages answer 403 here (15). Per the 8 October check, not re-read on 4 November, 2,849 open issues, 125 labelled bug, 1,599 opened before 8 July, and 78 closed in the last 30 days against 686 opened (6). Calendar versions in semver syntax, with a Breaking Changes section and an upgrade guide in release notes, but breaking changes arrive in ordinary releases and 2026.916.0 carried five (10). No 1.0. The npm latest tag is called the stable channel and follows a beta soak of at least three days, while the roadmap says the product is still moving quickly, so half credit (8). 20 + 15 + 6 + 10 + 8 = 59.

Score by category

CategoryWeightherdrPaperclipEdge
Reliability16%6559herdr +6
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%9181herdr +10
Agent ergonomics13%7370herdr +3
Security & auth14%4964Paperclip +15
Payments & pricing10%9090even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%6378Paperclip +15
Transparency & trust7%7066herdr +4
Negative events≤150-15
TotalBB 71.1/100C 56.4/100

Facts side by side

FactherdrPaperclip
KindAgent harnessAgent harness
VendorherdrPaperclip Labs, Inc.
Hosted endpointno (local only)no (local only)
Transports
AuthNoneOAuth or key
PricingFreeFree
x402nono
LicenceApache-2.0MIT
Read-only variant documentednono
llms.txtyesyes
Last release2026-10-142026-10-23
Terms last updatedno document linked2026-07-23
Privacy policy last updated2026-11-022026-07-23
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
Popularity52k stars99k stars, 60k npm/wk

How the scores have moved

Verdicts

herdr

Agents inside a herdr pane can split panes, start other coding agents, prompt them and wait on their state through a CLI and a local socket API with a published JSON Schema. It is pre-1.0 local software with no sandbox, and any process in a pane can type into another agent's terminal.

Paperclip

Board approvals, budgets with a hard stop and an activity log sit above whichever harnesses do the work, with ten stable versions in 90 days. The Claude Code and Codex adapters skip permission prompts and the sandbox by default, twelve security advisories have appeared since April 2026, and a 24 October cross-company read fix is in no stable release.

Before you call either

herdr

  1. Check HERDR_ENV=1 before any herdr command. If it isn't set, tell the person you aren't inside herdr and stop
  2. Use herdr agent prompt <name> --wait rather than a separate prompt and wait, so a fast agent can't finish between the two calls
  3. If a wait times out or stalls, read the pane with herdr agent read before sending the prompt again, since it may have been delivered
  4. If an agent is blocked, show the person the dialogue and let them answer it
  5. Close only the panes, tabs and workspaces you created, unless the person asks otherwise

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, herdr or Paperclip?

herdr scores 71.1 (BB) on agent readiness against Paperclip's 56.4 (C), and leads in 4 of 7 scored categories. Paperclip leads on security & auth and maintenance & community.

Are herdr and Paperclip open source?

Yes. herdr is open source (Apache-2.0). Paperclip is open source (MIT).

Other comparisons with herdr 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.