Head to head · Agent harnesses · October 2026 research run

Agent Zero vs Friday

Friday scores 65.3 (B) on agent readiness against Agent Zero's 49.7 (D), and leads in 4 of 7 scored categories. Agent Zero leads on reliability, payments & pricing and maintenance & community. Both do agent harnesses.

Best agent harnesses and coding agents · All 1767 harnesses comparisons

Which one, for what

Agent Zero D

Best for A technical owner who wants an agent with its own Linux machine, reachable from Telegram, WhatsApp or email, with scheduled tasks and editable memory.

Ahead on

  • Reliability, 57 against 45
  • Payments & pricing, 90 against 60
  • Maintenance & community, 75 against 70

Watch for

No approval step before shell commands, file changes or outgoing messages. Tool Access defaults to allow

Friday B

Best for A person who already runs several coding CLIs and wants an outside agent to hand work to them and wait on the result.

Ahead on

  • Schema & documentation, 82 against 64
  • Agent ergonomics, 78 against 62
  • Security & auth, 61 against 54

Also in its favour

  • Runs on your own machine
  • No incidents deducted, where Agent Zero loses 15 points for them

Watch for

Version 0.3.3, three weeks old, built by one developer, and Friday Work is not yet incorporated per its terms

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 Agent Zero +30

Agent Zero 90

Read with the self-hosted rule. No payment protocol in the source (0). Free under MIT with nothing to buy for the software, so 20, 20 and 20 on the last three lines. It starts with one Docker command and no account. Model usage is billed by whichever provider the owner configures, or costs nothing with a local model. The vendor's site also describes a beta LLM API whose daily quota depends on staking its A0T token. That is separate from the software and not scored. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 60 is 90.

Friday 60

Scored on the hosted option, as for Orca. No payment protocol (0). Friday Team is priced on request, with no price on the pages read (0). The app is free and MIT licensed with no card (30). The app needs no account or sign-up (30). 0 + 0 + 30 + 30 = 60.

Schema & documentation Friday +18

Agent Zero 64

Harness reading of the lines, as the Goose calibration dossier does. No OpenAPI file. The connectivity page lists five external endpoints and the X-API-KEY header, then sends readers to the source or DeepWiki for request and response details. Each API handler and tool has a .dox.md contract file in the repository, and the MCP client JSON shape is documented (10 of 25). llms.txt at www.agent-zero.ai, and AGENTS.md contract files across the repository (10). Guides say which path to use for a need, with tables that separate the browser, the host connector, MCP and A2A (14 of 20). The v2.12 notes say 15 bundled tools gained argument descriptions in non-strict schemas, and plugin settings are typed YAML with commented examples (8 of 15). Guides carry worked examples and a troubleshooting page, with no documented error responses for the external API (9 of 15). Dated notes on every GitHub release and a release article for each version on the site, with no version prefix on API routes (13 of 15).

Friday 82

Read on the outside-agent MCP server. Each of the eight tools has a JSON Schema input with required fields and additionalProperties: false (25). llms.txt, llms-full.txt and every page as Markdown with Accept: text/markdown (10). Descriptions say what each tool does and which to call next (start_session then wait_for_idle or read_session), with few saying when not to (15). Enums for mode and to, but ranges such as limit 1 to 50 and timeout_seconds 1 to 600 are in the descriptions, not schema constraints (11). Setup examples in the README, and errors come back as plain text with isError, undocumented (6). Semver tags and a dated public changelog (15). 25 + 10 + 15 + 11 + 6 + 15 = 82.

Agent ergonomics Friday +16

Agent Zero 62

Harness reading, scored on what a person or program driving it must supply. Skills load on demand, blocked tools are removed from the prompt, chats can be compacted, and the v2.12 notes report Codex input falling from about 16.4K to 11.3K tokens, a vendor figure (18 of 25). An MCP tool timeout of 120 seconds, a limit of five consecutive unusable responses and context-window handling are set by default. No turn or spend limit was found in the reviewed docs (11 of 20). Other programs reach it through POST /api_message, an optional MCP server, A2A and an ACP bridge, with request and response shapes left to the source (11 of 20). An error-retry plugin, saved chats, a message queue, backups and Time Travel snapshots with diff and revert (14 of 20). One Docker command starts it and a wizard sets the model, but there is no SDK and the default has no login (8 of 15).

Friday 78

Eight compact tools (25). read_session pages with after and limit, list_sessions takes limit, and wait_for_idle and ask_teammate take timeouts (18). Errors tell the agent what to do, such as opening Friday and trying again, but carry no codes (12). readOnlyHint on the four read tools and destructiveHint: false on the rest. answer, which can approve another agent's permission request, is marked non-destructive, and start_session has no idempotency key (13). Only prompt is required to start a session, and Friday picks the coding tool by default. No SDK, which a desktop app doesn't need (10). 25 + 18 + 12 + 13 + 10 = 78.

Reliability Agent Zero +12

Agent Zero 57

Read with the local-software lines, as software the owner runs. Installs from the agent0ai/agent-zero Docker image, an install script, or a desktop Launcher with builds for macOS, Linux and Windows on x86 and ARM64. The README says it runs wherever Docker runs. The image registry page was not read (17 of 20). The repository holds 245 files under tests/ on 4 November, and its only two workflows still publish Docker images and close inactive issues. The publish workflow runs no tests, so no public CI run shows them passing (5 of 25, a partial kept). 139 open issues and pull requests on 12 October 2026, per that check (GitHub's pages and API weren't read on 4 November). Open reports from September include a crash of run_ui after a failed memory consolidation (#1909), a browser worker that hangs the agent turn (#1923) and truncated backups (#1904), each with no reply or one, and a workflow closes anything inactive for 90 days (11 of 25). Release notes for v2.11, v2.12 and v2.13 carry a Breaking Changes section, but breaking changes ship in minor versions, so the numbering is not semver (9 of 15). v2.15, past 1.0 (15).

Friday 45

Read as local software, as for herdr and Orca. Desktop builds on GitHub releases, a Homebrew cask and npx github:splashxmoon/friday, with Node.js 22 stated (20). .github/workflows/ci.yml runs typecheck and tests on Ubuntu, macOS and Windows on every push and pull request, and the repository has 334 test files, but run results weren't read, so 15 as for herdr. Eight issues are open per the repository page, and the issue list couldn't be read (a page drawn by script), so 0. Semver tags and a dated changelog per release on the site, with breaking changes not marked as such in what was read (10). Version 0.3.3, not 1.0 (0). 20 + 15 + 0 + 10 + 0 = 45.

Security & auth Friday +7

Agent Zero 54

Harness reading of the framework checklist, the one the Goose calibration dossier uses. 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. No usage telemetry was found in the source. An update check, on by default, posts the version and a 20-character SHA-256 hash of a random per-install id to api.agent-zero.ai. The Update Checker settings page says only that ID and the version are sent and has an off switch. Something still leaves the machine by default, so the partial is kept (22). The agent works inside a Docker container built on Kali Linux and runs as root there. Tool Access can block tools by project or profile and defaults to allow, host access through the A0 CLI is scoped by read, write and execute permissions, and no approval step was found before a shell command, a file deletion or an outgoing message. The web interface has no login until a username is set (10). Infection Check audits the agent's reasoning with a second model before each tool call and ships disabled. Scanners check plugins, skills and MCP servers before install. The channel allow-lists accept every sender when empty, and the email filter matches the claimed From address only, which the plugin README states (7). Chat logs, visible tool steps and Time Travel snapshots, with no per-call audit log. Per-process log files were removed in v2.5 (9). No SECURITY.md on 4 November, security.txt answered 404 on 12 October, and none of the eight CVEs published from 17 March to 22 October 2026 came from the vendor (VulDB, VulnCheck, MITRE and CISA assigned them). A security-review ledger in the repository records two findings, and the v2.12 notes name both fixes (6, a partial kept).

Friday 61

Harness reading, as for herdr. 127.0.0.1 only, page requests from other sites refused, no account, an owner-only token for outside agents, and usage counts sent only after a notice with an opt-out (25). Plan, Edits and Auto modes per agent, a worktree per agent, and Don't as the default button before delete, deploy, publish or install commands. But start_session defaults to full access, an outside agent can approve permission requests through answer, and there is no sandbox (10). Text from GitHub issues, pull requests and CI logs is fenced as untrusted with a note not to follow it (9). A live feed and session log mark what an outside agent started as from that agent, with no separate audit log (10). SECURITY.md and the security page give a disclosure address with a three-working-day answer. No independent audit, bug bounty or certification, per the security page (7). 25 + 10 + 9 + 10 + 7 = 61.

Maintenance & community Agent Zero +5

Agent Zero 75

v2.15 was tagged on 1 November 2026, 3 days before this check (30). Seven releases from 6 August, v2.9 on 12 August to v2.15, read from the clone's tags (20). Of the 40 newest open items read on 12 October, 16 are issues and 14 of those have no comment. Three security reports filed as issues were closed as completed, one in five days and two after three months. GitHub's issue pages weren't read on 4 November, so this is per the 12 October check (10 of 25). The Docker image, the desktop Launcher, the install scripts and the A0 CLI connector come from the same organisation, and the v2.14 notes point the README's Launcher links to v1.9 (10 of 15). A Docker publish workflow builds images from tags, and the v2.14 notes raise dependency security floors for aiohttp, anyio, urllib3, filelock, fsspec and multidict. No public test CI (5 of 10). 30 + 20 + 10 + 10 + 5 = 75.

Friday 70

v0.3.3 on 17 November 2026, one day before the check (30). 36 releases since 26 October 2026 (20). Issues couldn't be read. CONTRIBUTING.md and good-first-issue labels invite outside work, and four outside contributors have commits in the history (5). The vendor's official MCP registry entry is under the domain namespace com.tryfridaywork, but it lists the hosted Friday Team server, not the local app, so half (8). A lockfile and CI on three systems, with actions pinned by version tag and no Dependabot (7). 30 + 20 + 5 + 8 + 7 = 70.

Score by category

CategoryWeightAgent ZeroFridayEdge
Reliability16%5745Agent Zero +12
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%6482Friday +18
Agent ergonomics13%6278Friday +16
Security & auth14%5461Friday +7
Payments & pricing10%9060Agent Zero +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%7570Agent Zero +5
Transparency & trust7%6468Friday +4
Negative events≤15-150
TotalD 49.7/100B 65.3/100

Facts side by side

FactAgent ZeroFriday
KindAgent harnessAgent harness
VendorAgent Zero, s.r.o.Friday Work
Hosted endpointno (local only)no (local only)
Transportsstdio
AuthNoneNone
PricingFreeFree
x402nono
LicenceMITMIT
Tools exposednone8
Read-only variant documentednono
llms.txtyesyes
MCP registrynot listedcom.tryfridaywork/friday-work
Last release2026-11-012026-11-17
Terms last updatedno document linked2026-11-01
Privacy policy last updatedno document linked2026-11-01
Customer content may train modelsnot read yetnot found in the text
Terms restrict automated accessnot read yetnot found in the text
Terms restrict benchmarkingnot read yetyes
Terms or service can change without noticenot read yetnot found in the text
Arbitration or class-action waivernot read yetnot found in the text
Popularity19k stars81 stars

How the scores have moved

Verdicts

Agent Zero

Self-hosted under the MIT licence, with seven releases from 12 August to 1 November 2026 and breaking changes listed in minor-release notes. The agent runs shell commands in its container with no approval step, the web interface has no login by default, and eight CVEs from the past year were published by third parties with no vendor advisory.

Friday

Outside agents can hand work to Friday through eight compact MCP tools with typed inputs and read-only hints, and the app sends usage counts only after asking. It is a three-week-old 0.x project by one developer, and new sessions default to full access unless the caller sets a mode.

Before you call either

Agent Zero

  1. Set a UI login and password in Settings before publishing the port or opening a tunnel. The default has none
  2. Fill allowed_users, allowed_numbers or sender_whitelist before enabling a channel. An empty list accepts every sender
  3. Enable the Infection Check plugin when the agent reads mail, web pages or MCP results. It ships disabled
  4. Run v2.12 or later. It fixes a Telegram webhook authentication bypass and a WhatsApp media path traversal
  5. Call POST /api_message with the X-API-KEY header. The token changes when the UI login or password changes

Friday

  1. Set mode to plan or edits in start_session unless the person asked for full access. The default is full
  2. Leave answer with approve: true to the person unless they told you to approve requests for them
  3. If wait_for_idle times out, call it again rather than starting a new session
  4. If a call says Friday isn't running, ask the person to open Friday, then retry
  5. Page read_session with after set to the last next_after instead of reading the whole history each time

Questions

Which is better for AI agents, Agent Zero or Friday?

Friday scores 65.3 (B) on agent readiness against Agent Zero's 49.7 (D), and leads in 4 of 7 scored categories. Agent Zero leads on reliability, payments & pricing and maintenance & community.

Are Agent Zero and Friday open source?

Yes. Agent Zero is open source (MIT). Friday is open source (MIT).

Other comparisons with Agent Zero or Friday

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.