Head to head · Agent harnesses · October 2026 research run

Agent Zero vs Emdash

Emdash scores 53.9 (D) on agent readiness against Agent Zero's 46 (D), and leads in 0 of 7 scored categories. Agent Zero leads on schema & documentation, agent ergonomics, security & auth, maintenance & community and transparency & trust. Both do agent harnesses.

Best agent harnesses and coding agents · All 1500 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

  • Schema & documentation, 64 against 55
  • Agent ergonomics, 62 against 55
  • Security & auth, 54 against 38
  • Maintenance & community, 75 against 70
  • Transparency & trust, 64 against 54

Watch for

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

Emdash D

Best for Developers who want parallel agents in worktrees, fed from their issue tracker, locally or over SSH.

Also in its favour

  • No incidents deducted, where Agent Zero loses 15 points for them

Watch for

Telemetry on unless turned off in Settings or with TELEMETRY_ENABLED=false

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 Agent Zero +16

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).

Emdash 38

Harness reading. Telemetry is described as optional and disabled in Settings or with TELEMETRY_ENABLED=false, which reads as on by default (15 of 30). Worktree per task and remote machines over SSH (10 of 20). No prompt-injection guidance (5). No audit log (5). No security policy file found (3). 15 + 10 + 5 + 5 + 3 = 38.

Transparency & trust Agent Zero +10

Agent Zero 64

MIT, copyright Agent Zero, s.r.o. (30). No privacy policy for the software was found. The site's cookie notice covers the website, and its terms (14 May 2026) cover the community platform. The docs say where data lives (chats, memory, secrets and settings under /a0/usr) and warn that model providers see what is sent to them only in general terms, with no retention statement (8 of 30). Release notes list breaking changes and removals with the release date, and one deprecated alias is named. No deprecation policy or notice period was found (8 of 20, a partial kept). No usage telemetry was found in the source. The update check is described on its settings page, which says it sends only a randomised, hashed install ID and the version number, and the same page turns it off. The ID is a hash of a random per-install token, a pseudonym under this run's reading, so the statement holds (20). 30 + 8 + 8 + 20 = 66.

Emdash 54

Apache 2.0 (30). A telemetry page on the docs site (not read) (18 of 30). No deprecation policy (5). Disclosed with an opt-out (15 of 20). 30 + 18 + 5 + 15 = 68.

Schema & documentation Agent Zero +9

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).

Emdash 55

Harness reading. Docs site and a workspace server package (55).

Agent ergonomics Agent Zero +7

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).

Emdash 55

Harness reading. Issue intake from Linear, GitHub, Jira and others, diff review, pull requests and CI checks in one place, local or over SSH (55).

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.

Emdash 70

v1.2.11 on 6 November 2026 (30). v1.2.9, v1.2.10 and v1.2.11 within two weeks (20). GitHub issues and pull requests weren't read (GitHub's pages refuse these sessions), so that line is scored absent (0). Current installers and Homebrew cask (15). Release workflows, no test CI (5). 30 + 20 + 0 + 15 + 5 = 70.

Score by category

CategoryWeight this runAgent ZeroEmdashEdge
Reliability16%205755Agent Zero +2
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.26455Agent Zero +9
Agent ergonomics13%16.26255Agent Zero +7
Security & auth14%17.55438Agent Zero +16
Payments & pricing10%12.56060even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87570Agent Zero +5
Transparency & trust7%8.86454Agent Zero +10
Negative events≤15-150
TotalD 46/100D 53.9/100

Facts side by side

FactAgent ZeroEmdash
KindAgent harnessAgent harness
VendorAgent Zero, s.r.o.General Action, Inc.
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceMITApache-2.0
Read-only variant documentednono
llms.txtyesno
Last release2026-11-012026-11-06
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno document linked
Popularity19k starsnone

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.

Emdash

A mature open-source app for parallel coding agents in Git worktrees, with issue intake from a dozen trackers and remote machines over SSH. Telemetry is on unless you turn it off, and no test workflow was found in the repository.

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

Emdash

  1. Launch with TELEMETRY_ENABLED=false if you don't want telemetry
  2. Use the SSH mode to keep agents on a remote machine

Questions

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

Emdash scores 53.9 (D) on agent readiness against Agent Zero's 46 (D), and leads in 0 of 7 scored categories. Agent Zero leads on schema & documentation, agent ergonomics, security & auth, maintenance & community and transparency & trust.

Are Agent Zero and Emdash open source?

Yes. Agent Zero is open source (MIT). Emdash is open source (Apache-2.0).

Other comparisons with Agent Zero or Emdash

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.