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

Devin vs herdr

herdr scores 71.1 (BB) on agent readiness against Devin's 58.5 (C), and leads in 4 of 7 scored categories. Devin leads on security & auth and transparency & trust. Both do multi-agent orchestration.

Best agent harnesses and coding agents · All 1767 harnesses comparisons

Which one, for what

Devin C

Best for A team that wants to hand whole tasks to a cloud agent and collect pull requests, driven from a pipeline or another agent.

Ahead on

  • Security & auth, 72 against 49
  • Transparency & trust, 75 against 70

Also in its favour

  • A hosted endpoint, with nothing to install

Watch for

www.devinstatus.com lists two outages on 13 August and the web app down for about two hours on 24 September 2026

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 35
  • Schema & documentation, 91 against 80
  • Agent ergonomics, 73 against 62
  • Payments & pricing, 90 against 30

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

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.

Payments & pricing herdr +60

Devin 30

Published rubric. No payment protocol (0). Plan prices are public, $20, $200 and $40 a seat with an $80 team minimum, but usage past the quota is billed at an unpublished rate (10). A Free plan exists. The pricing page lists cloud agents from Pro upward, and we couldn't confirm API use on Free or whether a card is needed (10). A person signs up in a browser and provisions the service user in settings (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 20 is 30.

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.

Reliability herdr +30

Devin 35

Hosted reading. Status page at www.devinstatus.com (Atlassian Statuspage) with 14 components, among them Cloud Agent and Cloud Web Client, read from the page itself on 4 November 2026 (20). Its history feed for the 90 days from 6 August 2026 lists Devin unavailable on 13 August (20 minutes), Devin Cloud unavailable on 13 August (2 hours 40 minutes) and the web app down on 24 September (about 2 hours), with minor session and Ask Devin incidents on 10 and 11 August, 3 and 17 September and 26 October. Both 13 August entries report the service unavailable. The 24 September entry names only the web app, not the API or the MCP server, so it is read as partial, as dashboard outages are on other listings. Two majors (5). Two scheduled maintenance entries (7 and 17 August) are read as maintenance. 429 is a documented response, but no rate limit figures were found (0). No Retry-After or backoff guidance found, and v3 session creation has no idempotency key (0). The platform terms give no guarantee of availability, and enterprise terms weren't read (0). The v3 API is the current, recommended surface, with 27 of 274 operations under /v3beta1 (10).

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.

Security & auth Devin +23

Devin 72

Hosted reading. Service-user keys with roles and named permissions per endpoint, revocable, with rotation endpoints in beta for Enterprise and expiring personal tokens. Custom roles are an Enterprise option, and Teams has Admin and Member only (25). Security profiles restrict network, MCP servers, git and the Devin MCP to read-only, and read-only API permissions exist. They are opt-in, and session creation accepts bypass_approval (16). AI Guardrails screen user messages and pull request comments for prompt injection, on Enterprise only, and they don't cover web pages or repository content Devin reads (8). Audit logs through the API need an enterprise-level permission. Session events and insights are available on all plans (10). SOC 2 Type II and ISO/IEC 27001:2022, a disclosure address at security@cognition.ai, no security.txt, and the trust centre answers No to having a bug bounty (13).

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.

Schema & documentation herdr +11

Devin 80

API reading. Public OpenAPI 3.1 spec for v3 with 182 paths and 274 operations on 4 November 2026, and separate v1 and v2 specs (25). llms.txt with 393 lines and a Markdown twin of every page (10). Each endpoint page names its required permission, but 63 of 274 operations have no description and the MCP tool descriptions are one line each (10). Enums on fields such as devin_mode, origin and category, with most strings unconstrained and nullable (9). curl examples in the quick starts, and 401, 403, 404, 409, 422 and 429 declared on all 274 operations, without a catalogue of error_code values (11). Versioned paths (v1, v2, v3, v3beta1) and an API release notes page dated by month, newest November 2026 (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.

Agent ergonomics herdr +11

Devin 62

API and MCP reading. The MCP server documents 13 tools, several of them consolidated manage tools, and list endpoints take first to size a page (17). Cursor pagination on every v3 list endpoint and filters on session search by tag, playbook, origin, user and time (18). problem+json with error_code, field-level errors on 422 and a 400 that lists valid platform names, but no published code list (15). No idempotency key on v3 session creation. max_acu_limit caps what a session can spend, and the MCP tool annotations couldn't be read without a key (4). Only prompt is required to start a session. No official SDK found, only a Terraform provider (8).

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.

Transparency & trust Devin +5

Devin 75

Editorial half. Closed source with clear terms from Cognition AI, Inc. (15). Terms (30 June 2026), privacy policy, security page and data processing agreement agree with each other. Customer data may be used for model training by default on self-serve plans, with an opt-out on paid plans that also turns on zero data retention at model providers, and Enterprise data isn't trained on without written consent. Retention is stated as the length of the customer relationship, with no periods (18). The API versioning policy on the release notes page says breaking changes are announced at least 7 days in advance and a deprecated endpoint stays available through a deprecation period. Dated notices followed it for the schedules endpoints (announced 10 September, creation refused from 24 September 2026), and others cover the v2 clone endpoint and Playbooks moving to Skills (23 October). v1 and v2 are marked legacy with no end date (20). Sub-processors listed with purpose and country, and 15 days' notice of additions, per the 8 October check (18).

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.

Score by category

CategoryWeightDevinherdrEdge
Reliability16%3565herdr +30
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%8091herdr +11
Agent ergonomics13%6273herdr +11
Security & auth14%7249Devin +23
Payments & pricing10%3090herdr +60
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%6363even
Transparency & trust7%7570Devin +5
Negative events≤1500
TotalC 58.5/100BB 71.1/100

Facts side by side

FactDevinherdr
KindAgent harnessAgent harness
VendorCognition AI, Inc.herdr
Hosted endpointhttps://mcp.devin.ai/mcpno (local only)
TransportsHTTP
AuthAPI keyNone
PricingFreemiumFree
x402nono
LicenceProprietary service under Cognition's Platform Terms of ServiceApache-2.0
Tools exposed13none
Read-only variant documentedyesno
llms.txtyesyes
Last release2026-11-022026-10-14
Terms last updated2026-06-30no document linked
Privacy policy last updated2026-03-092026-11-02
Customer content may train modelsyes, with an opt-outnot read yet
Terms restrict automated accessnot found in the textnot read yet
Terms restrict benchmarkingyesnot read yet
Terms or service can change without noticenot found in the textnot read yet
Arbitration or class-action waiveryesnot read yet
Popularitynone52k stars

How the scores have moved

Verdicts

Devin

The v3 API is well specified, with a public OpenAPI 3.1 file covering 274 operations, problem+json errors, cursor pagination and service-user keys tied to roles. The status page records two outages on 13 August and a two-hour web app outage on 24 September 2026, and no rate limit figures or retry guidance were found in the reviewed documentation.

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.

Before you call either

Devin

  1. Use a cog_ service-user key with the Member role. Legacy apk_ keys fail against v3 and the MCP server with 401 or 403
  2. Set max_acu_limit on every session you create. Usage is metered by the work done and has no published unit rate
  3. Session creation is not idempotent in v3. After a timeout, list sessions by tag before creating again
  4. Enterprise keys and personal access tokens must send X-Org-Id to the MCP server. Organisation-scoped keys resolve it automatically
  5. Create scheduled work as an automation. POST to the schedules endpoint returns 403 for migrated organisations since 24 September 2026

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

Questions

Which is better for AI agents, Devin or herdr?

herdr scores 71.1 (BB) on agent readiness against Devin's 58.5 (C), and leads in 4 of 7 scored categories. Devin leads on security & auth and transparency & trust.

Are Devin and herdr open source?

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

Other comparisons with Devin or herdr

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.