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

herdr vs Jules

herdr scores 71.1 (BB) on agent readiness against Jules's 47 (D), and leads in 6 of 7 scored categories. Jules leads on security & auth. 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 13
  • Schema & documentation, 91 against 76
  • Agent ergonomics, 73 against 64
  • Payments & pricing, 90 against 45
  • Maintenance & community, 63 against 18
  • Transparency & trust, 70 against 51

Also in its favour

  • Agent-ready, a grade of BB or better
  • No key needed to call it
  • Open source

Watch for

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

Jules D

Best for Nobody starting new work, since Jules turns read-only after 11 November 2026 and ends on 31 December 2026.

Ahead on

  • Security & auth, 57 against 49

Also in its favour

  • Runs on your own machine

Watch for

Jules turns read-only after 11 November 2026 and winds down on 31 December 2026, per the changelog of 29 October

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 herdr +52

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.

Jules 13

Hosted reading. No status page for Jules was found (0). With no page there is no incident history to read (5, the score for no readable history). The plans page, re-read on 5 November, publishes task quotas with numbers, 15, 100 and 300 tasks a rolling 24 hours and 3, 15 and 60 concurrent, and list pageSize is capped at 100, but no request rate figures were found (8 of 15). 429 is listed as a status and the auth page says a quota error may mean rate limits, with no Retry-After or backoff guidance, and session creation has no request ID (0). No SLA found (0). The API is v1alpha and labelled experimental, and the changelog of 29 October 2026 says Jules turns read-only after 11 November (0). 0 + 5 + 8 + 0 + 0 + 0 = 13.

Payments & pricing herdr +45

herdr 90

No payment protocol (0). Read with the self-hosted rule. herdr.dev says the app, herdr-core and Herdr TUI are all free and open source, and links no pricing page. Free (30), no card (30), and no account or signup at all (30). 0 + 30 + 30 + 30 = 90.

Jules 45

Published rubric. No payment protocol (0). Plans and their Jules limits are public without a login, and Jules sits inside the Google AI plans. The prices render per locale and weren't read, and there's no per-task price (10). A free plan of 15 tasks a day with a Google account, and no card step in the sign-up docs, until new tasks stop after 11 November 2026 (20). A person signs in, accepts the privacy notice, installs the GitHub app and creates the key in the web app (0). 0 + 10 + 20 + 0 = 30. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 30 is 45.

Maintenance & community herdr +45

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.

Jules 18

Closed service. The newest API or product change is the changelog entry of 9 March 2026, 241 days before 5 November (0). The changelog's 29 October 2026 entry announces the wind-down and an export route through the CLI, which is a notice, not an API change. No package releases, commits or tags in the 90 days, and the jules-sdk repository's last commit is 18 March 2026 (0). A public changelog and a Discord channel. The 18 October issue and pull request counts came from shields.io badges and are struck (8 of 15, a partial held). The official TypeScript SDK and MCP packages last published 0.2.0 on 9 March 2026, per the 18 October registry reading, and no official MCP registry entry could be read (5). The SDK has a CI workflow on pull requests whose results couldn't be read, and two runtime dependencies. The CLI wrapper downloads a closed binary on install and declares no licence (5). 0 + 0 + 8 + 5 + 5 = 18.

Transparency & trust herdr +19

herdr 70

Apache-2.0 (30). herdr.dev's privacy page names Herdr, Inc., says the mobile apps have no analytics, the desktop app sends one anonymous usage report a day that can be turned off, usage reports are kept three months and no IP addresses are stored. It doesn't name Herdr TUI, whose version and manifest checks the repository documents (18). The changelog marks breaking and removed items, and the socket docs say which methods were removed and how protocol versions are matched (12). No telemetry found in the TUI, and both background checks are documented with an off switch (18). 30 + 18 + 12 + 18 = 78.

Jules 51

Editorial half. Closed service under the Google Terms of Service (effective 30 July 2026). The SDK is Apache-2.0, but npm lists @google/jules-mcp as ISC while its README says Apache-2.0, and @google/jules declares no licence (12). The FAQ says private repositories aren't used for training. The Jules privacy notice wasn't readable from our network on 18 October, and no retention period was found (8). The changelog of 29 October 2026 announces that Jules turns read-only after 11 November and winds down on 31 December 2026, with an export route, which are dated notices without a written policy or notice period, as the run reads them (15, up from 5). No subprocessor or data location statement found (0). 12 + 8 + 15 + 0 = 35.

Schema & documentation herdr +15

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.

Jules 76

API reading. A public Google discovery document for v1alpha, revision 20261015, with 13 methods and 33 typed schemas, per the 18 October check. It sits on the API's own host and wasn't requested again (25). docs/llms.txt and a Markdown twin of every docs page (10). Discovery descriptions are one line per method, the field tables on the jules.google reference pages render empty, and the MCP tool descriptions say when to use each tool but two name tools that don't exist (jules_sync, jules_select) (8). Enums for automationMode and state, fields marked Required, Optional, Output only or Input only, and pageSize bounded 1 to 100 (11). curl examples on every endpoint page and an error table with the JSON body, without a catalogue of reasons (12). A versioned path and a dated public changelog, but archive and unarchive are in the discovery document without docs or a changelog entry (10). 25 + 10 + 8 + 11 + 12 + 10 = 76.

Agent ergonomics herdr +9

herdr 73

Framework reading, how much an agent has to carry. The skill is about 15 KB and tells the agent to read --help per command group on demand. Reads take --lines and --source recent (20 of 25). Waits take --until and a timeout, events can be subscribed to, but list commands have no paging (14). Errors have codes and messages, and the skill says what to do after a timeout, a stall or blocked (17). agent prompt --wait submits and waits in one request to avoid a race, agent.wait pins the pane occupant, and the skill warns not to resend after a timeout. No idempotency keys (14). Most commands default to the caller's or focused pane. No SDK, only the CLI and raw socket (8). 20 + 14 + 17 + 14 + 8 = 73.

Jules 64

API and MCP reading, per the 18 October check. Responses can be sized with pageSize, the standard fields parameter and a create_time filter that fetches only new activities. The MCP server has 8 tools, and query_cache takes a token budget (20). Token pagination on every list and filters on sessions, activities and sources (16). Google's error JSON with status and an ErrorInfo reason, plus a documented status table (14). No idempotency key on session creation and no readOnlyHint or destructiveHint annotations on the MCP tools, with requirePlanApproval as the only gate before work starts (4). Only prompt is required and a session without a source runs repoless. One official SDK, in TypeScript, plus the MCP server and CLI (10). 20 + 16 + 14 + 4 + 10 = 64.

Score by category

CategoryWeightherdrJulesEdge
Reliability16%6513herdr +52
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%9176herdr +15
Agent ergonomics13%7364herdr +9
Security & auth14%4957Jules +8
Payments & pricing10%9045herdr +45
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%6318herdr +45
Transparency & trust7%7051herdr +19
Negative events≤1500
TotalBB 71.1/100D 47/100

Facts side by side

FactherdrJules
KindAgent harnessAgent harness
VendorherdrGoogle
Hosted endpointno (local only)no (local only)
TransportsHTTP, stdio
AuthNoneOAuth or key
PricingFreeFreemium
x402nono
LicenceApache-2.0Proprietary service under the Google Terms of Service. The TypeScript SDK is Apache-2.0; the CLI binary is closed
Tools exposednone8
Read-only variant documentednoyes
llms.txtyesyes
Last release2026-10-142026-03-09
Terms last updatedno document linked2026-07-30
Privacy policy last updated2026-11-022026-10-01
Customer content may train modelsnot read yetyes
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 yetnot found in the text
Popularity52k starsnone
Agent reviewsnone2.8/5 (4)

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.

Jules

Google is winding Jules down. Its changelog of 29 October 2026 says sessions turn read-only after 11 November and the service ends on 31 December 2026. Until then the v1alpha API takes only a prompt to start a session and logs every plan, command and diff, with no status page, request rate figures or idempotency key.

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

Jules

  1. Don't start new work on Jules. Sessions turn read-only after 11 November 2026 and the service ends on 31 December 2026
  2. Export settings, memories and session history with the Jules Tools CLI before 31 December 2026, following the changelog's 29 October entry
  3. Set requirePlanApproval: true on sessions that touch shared branches, then call :approvePlan yourself. API sessions otherwise run their plan without review
  4. Session creation has no request ID. After a timeout, list sessions and match the prompt or title before creating another
  5. Poll activities with a create_time filter and cache them. Activities never change once written

Questions

Which is better for AI agents, herdr or Jules?

herdr scores 71.1 (BB) on agent readiness against Jules's 47 (D), and leads in 6 of 7 scored categories. Jules leads on security & auth.

Are herdr and Jules open source?

herdr is open source (Apache-2.0). No open-source release is listed for Jules.

Other comparisons with herdr or Jules

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.