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
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
| Category | Weight this run | Agent Zero | Emdash | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 57 | 55 | Agent Zero +2 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 64 | 55 | Agent Zero +9 |
| Agent ergonomics | 13%16.2 | 62 | 55 | Agent Zero +7 |
| Security & auth | 14%17.5 | 54 | 38 | Agent Zero +16 |
| Payments & pricing | 10%12.5 | 60 | 60 | even |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 75 | 70 | Agent Zero +5 |
| Transparency & trust | 7%8.8 | 64 | 54 | Agent Zero +10 |
| Negative events | ≤15 | -15 | 0 | |
| Total | D 46/100 | D 53.9/100 |
Facts side by side
| Fact | Agent Zero | Emdash |
|---|---|---|
| Kind | Agent harness | Agent harness |
| Vendor | Agent Zero, s.r.o. | General Action, Inc. |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | MIT | Apache-2.0 |
| Read-only variant documented | no | no |
| llms.txt | yes | no |
| Last release | 2026-11-01 | 2026-11-06 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Popularity | 19k stars | none |
How the scores have moved
Emdash
No score change since it was listed.
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
- Set a UI login and password in Settings before publishing the port or opening a tunnel. The default has none
- Fill
allowed_users,allowed_numbersorsender_whitelistbefore enabling a channel. An empty list accepts every sender - Enable the Infection Check plugin when the agent reads mail, web pages or MCP results. It ships disabled
- Run v2.12 or later. It fixes a Telegram webhook authentication bypass and a WhatsApp media path traversal
- Call
POST /api_messagewith theX-API-KEYheader. The token changes when the UI login or password changes
Emdash
- Launch with TELEMETRY_ENABLED=false if you don't want telemetry
- 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
- Agent Zero vs Aider
- Agent Zero vs Amp
- Agent Zero vs Antigravity CLI
- Agent Zero vs Auggie CLI
- Agent Zero vs AXLR
- Agent Zero vs Claude Code
- Agent Zero vs Cline
- Agent Zero vs Conductor
- Agent Zero vs Crush
- Agent Zero vs Cursor CLI
- Agent Zero vs DeepSeek Harness (dsh)
- Agent Zero vs dsh-superagent (DeepSeek)
- Agent Zero vs Devin
- Agent Zero vs Droid CLI
- Agent Zero vs Pi
- Agent Zero vs Gemini CLI
- Agent Zero vs GitHub Copilot CLI
- Agent Zero vs goose
- Agent Zero vs Harness²
- Agent Zero vs HarnessRouter
- Agent Zero vs Jules
- Agent Zero vs Junie CLI
- Agent Zero vs Kilo Code CLI
- Agent Zero vs Kimi Code CLI
- Agent Zero vs Kiro CLI
- Agent Zero vs Letta
- Agent Zero vs mini-swe-agent
- Agent Zero vs MiniMax Code
- Agent Zero vs Mistral Vibe CLI
- Agent Zero vs Muse Code
- Agent Zero vs OpenAI Agents API
- Agent Zero vs OpenAI Codex
- Agent Zero vs OpenCode
- Agent Zero vs OpenHands
- Agent Zero vs OpenMausBot
- Agent Zero vs Orca
- Agent Zero vs Paseo
- Agent Zero vs Prime Agent
- Agent Zero vs Qoder CLI
- Agent Zero vs Qwen Code
- Agent Zero vs Mirror CLI
- Agent Zero vs Rovo Dev CLI
- Agent Zero vs Sculptor
- Agent Zero vs T3 Code
- Agent Zero vs Traycer
- Agent Zero vs Unstoppable
- Agent Zero vs Verdent
- Agent Zero vs Vibe-Trading
- Agent Zero vs Warp (Warp Agent CLI and the Oz Agent API)
- Aider vs Emdash
- Amp vs Emdash
- Antigravity CLI vs Emdash
- Auggie CLI vs Emdash
- AXLR vs Emdash
- Claude Code vs Emdash
- Cline vs Emdash
- Conductor vs Emdash
- Crush vs Emdash
- Cursor CLI vs Emdash
- DeepSeek Harness (dsh) vs Emdash
- dsh-superagent (DeepSeek) vs Emdash
- Devin vs Emdash
- Droid CLI vs Emdash
- Pi vs Emdash
- Emdash vs Gemini CLI
- Emdash vs GitHub Copilot CLI
- Emdash vs goose
- Emdash vs Harness²
- Emdash vs HarnessRouter
- Emdash vs Jules
- Emdash vs Junie CLI
- Emdash vs Kilo Code CLI
- Emdash vs Kimi Code CLI
- Emdash vs Kiro CLI
- Emdash vs Letta
- Emdash vs mini-swe-agent
- Emdash vs MiniMax Code
- Emdash vs Mistral Vibe CLI
- Emdash vs Muse Code
- Emdash vs OpenAI Agents API
- Emdash vs OpenAI Codex
- Emdash vs OpenCode
- Emdash vs OpenHands
- Emdash vs OpenMausBot
- Emdash vs Orca
- Emdash vs Paseo
- Emdash vs Prime Agent
- Emdash vs Qoder CLI
- Emdash vs Qwen Code
- Emdash vs Mirror CLI
- Emdash vs Rovo Dev CLI
- Emdash vs Sculptor
- Emdash vs T3 Code
- Emdash vs Traycer
- Emdash vs Unstoppable
- Emdash vs Verdent
- Emdash vs Vibe-Trading
- Emdash vs Warp (Warp Agent CLI and the Oz Agent API)
- Clawboo vs Emdash
- CLI Manager vs Emdash
- Emdash vs Harness
- Emdash vs Paperclip
- Emdash vs Parallax
Machine-readable
- This page as Markdown
/compare/agent-zero-vs-emdash.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/agent-zero.json·/api/v1/tools/emdash.json - From a terminal
anchor compare agent-zero emdash(the CLI) - Over MCP
compare_tools {"a": "agent-zero", "b": "emdash"}at/mcp, no key