# Agent Zero > Agent Zero is an open-source agent framework that runs in a Docker container with a Linux desktop, a browser, a task scheduler and memory. Its owner reaches it through a web interface, Telegram, WhatsApp or email. - Canonical: https://www.anchorterminal.com/tools/agent-zero - Markdown: https://www.anchorterminal.com/tools/agent-zero.md (~8,600 tokens) - Slim: https://www.anchorterminal.com/tools/agent-zero.min.md (~1,830 tokens, same facts, less prose, for token-sensitive contexts) - JSON: https://www.anchorterminal.com/tools/agent-zero.json (this page as data, same URL with Accept: application/json) - Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt) - API: https://www.anchorterminal.com/api/v1/index.json - Updated: 2026-10-12 ## Overview **Grade C · 54.2/100 · rank #709 of 986 · #19 in Agent harnesses · not agent-ready · confidence medium** ## Assessment Self-hosted under the MIT licence, with nine releases in the 90 days to 12 October 2026 and breaking changes listed in the release notes. The agent runs shell commands in its container with no approval step, the web interface has no login by default, and five CVEs from the past year have no published GitHub advisory. ## Facts | Field | Value | | --- | --- | | Vendor | Agent Zero, s.r.o. (https://www.agent-zero.ai) | | Kind | Agent harness | | Category | Agent harnesses (https://www.anchorterminal.com/categories/agent-harnesses) | | Auth | None · No account. The web interface has no login until the owner sets a username and password in Settings or as `AUTH_LOGIN` and `AUTH_PASSWORD`, which are stored in `/a0/usr/.env` (https://github.com/agent0ai/agent-zero/blob/main/docs/setup/vps-deployment.md). The external API takes an `X-API-KEY` header, and the optional MCP server and A2A endpoint carry the same token in the URL path. The token is derived from the instance id and the login, so it changes when either changes (https://github.com/agent0ai/agent-zero/blob/main/docs/guides/a2a-setup.md). Model access uses provider API keys or OAuth sign-in to ChatGPT (Codex), GitHub Copilot, Google Cloud Gemini or xAI (https://github.com/agent0ai/agent-zero/blob/main/plugins/_oauth/README.md). | | Pricing | Free (Free · OSS) · Free under MIT, with nothing to buy for the software. The owner pays the model provider they configure, or nothing with a local model. A beta LLM API on the vendor's site gives a daily quota to people who stake its A0T token and is separate from the software (checked 2026-10-12). | | x402 | No · No x402, MPP or L402 in the docs or the source (checked 2026-10-12). | | Licence | MIT | | Packages | oci: `agent0ai/agent-zero` | | Source | https://github.com/agent0ai/agent-zero | | Docs | https://github.com/agent0ai/agent-zero/tree/main/docs | | llms.txt | https://www.agent-zero.ai/llms.txt | | Last release | 2026-09-23 | | GitHub stars | 19,429 (as of 2026-10-12) | | Where it runs | One Docker container on the owner's machine or server, built on Kali Linux, with a web interface on port 80, an XFCE desktop and a browser. The A0 CLI connector can extend it to host files, shell and browser | | Acts without asking | Shell commands, file edits and deletions, browser and desktop actions, MCP tool calls, scheduled tasks and replies on Telegram, WhatsApp and email all run without an approval step | | Controls | Tool Access allows or blocks each tool by project or agent profile and defaults to allow. Infection Check audits tool calls with a second model and ships disabled. Pause, stop and intervene controls in the interface. Time Travel snapshots can revert `/a0/usr` workspaces | | Proactive work | Scheduled (cron), planned (dated) and ad-hoc tasks, created in the interface or by the agent's `scheduler` tool, optionally bound to a project | | Channels | Web interface, Telegram bots (polling or webhook), WhatsApp through a Baileys bridge paired by QR code, and email by IMAP or Exchange polling with SMTP replies. The external API, MCP server, A2A and ACP serve other programs | | Who can message it | Per-channel allow-lists. An empty list accepts every sender. WhatsApp is disabled by default and no Telegram bot or mailbox is configured by default | | Accounts and credentials | A mailbox login for the email channel, a Telegram bot token, a linked WhatsApp session, and OAuth sign-in to ChatGPT (Codex), GitHub Copilot, Google Cloud Gemini or xAI for model access. No calendar or contacts connection is built in. Keys, passwords and secrets are stored in `.env`, `secrets.env`, `config.json` and `auth.json` files under `/a0/usr`, masked in prompts and the interface | | Memory | FAISS vector store with areas for main memories, fragments, solutions and skills. Automatic memorising and recall are on by default, and memory is isolated for each project by default. Chats are saved under `/a0/usr/chats` | | Deleting memory | The dashboard deletes one entry or many, and the agent has `memory_delete` and `memory_forget` tools. Backups and Time Travel snapshots made earlier can still hold a copy | | Model providers | 29 chat providers in the shipped list, among them Anthropic, OpenAI, Google, OpenRouter, Bedrock, Azure, Ollama, LM Studio, llama.cpp and vLLM, through LiteLLM. The provider chosen sees the conversation content | | Other outbound traffic | Update check to api.agent-zero.ai, on by default. Web search, browsing, MCP servers and tunnels (Cloudflare, Tailscale, Microsoft, Serveo) when the owner uses them | | MCP client | Command-based (stdio) and URL-based servers with headers, set as JSON in Settings, with a 120-second tool timeout by default and a scanner for new servers | | Cost | Free under MIT. Model usage is billed by the chosen provider, or nothing with a local model. The README says it runs on a $6 VPS | | Advisories | CVE-2026-4307 and CVE-2026-4308 (17 March 2026), CVE-2026-47119 (27 May 2026), CVE-2026-51852 and CVE-2026-51853 (30 September 2026), plus two flaws fixed in v2.12 on 9 September 2026. No GitHub advisory published | | Releases | v2.13 on 23 September 2026. Nine releases between 17 July and 23 September 2026 | | Capabilities | agent.harness, agent.mcp-client | | Tags | open-source, self-hosted, local, free, python, mit, llms-txt, docker | | JSON | https://www.anchorterminal.com/api/v1/tools/agent-zero.json | ## Score breakdown (methodology v0.4, October 2026 research run) Assessed 2026-10-12 from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/#checklist). Confidence: medium. Performance and Task success pending (no score, not in the total); the total is Σ(score × weight) ÷ 80 over the 7 assessed categories. "This run" is each category's share of the 100 points. | Category | Weight | This run | Score (0–100) | Points | | --- | --- | --- | --- | --- | | Reliability | 16% | 20 | 57 | 11.4 | | Performance | 10% | pending | pending | n/a | | Schema & documentation | 13% | 16.2 | 64 | 10.4 | | Agent ergonomics | 13% | 16.2 | 62 | 10.1 | | Security & auth | 14% | 17.5 | 54 | 9.4 | | Payments & pricing | 10% | 12.5 | 60 | 7.5 | | Task success | 10% | pending | pending | n/a | | Maintenance & community | 7% | 8.8 | 75 | 6.6 | | Transparency & trust (editorial 56, provenance 53) | 7% | 8.8 | 55 | 4.8 | | Negative events | up to −15 | up to −15 | 2026-03-17. CVE-2026-4307 (path traversal in `get_abs_path`, CVSS 4.3) and CVE-2026-4308 (server-side request forgery in document queries, CVSS 6.3), both against 0.9.7, with public exploits. The NVD entries say the vendor was contacted and did not respond. The v2.9 notes of 12 August 2026 list a fix for an SSRF regression under CVE-2026-4308. Whether CVE-2026-4307 is fixed was not established. -2. https://services.nvd.nist.gov/rest/json/cves/2.0?cveId=CVE-2026-4308 2026-05-27. CVE-2026-47119, stored cross-site scripting through SVG files served by the `image_get` endpoint, CVSS 6.1, in versions before 1.15. The report (#1609) was closed as completed on 12 May 2026. Fixed, and no GitHub advisory was published. -1. https://github.com/agent0ai/agent-zero/issues/1609 2026-09-30. CVE-2026-51852 and CVE-2026-51853, directory traversal in the file browser of versions 1.7 to 1.10, CVSS 7.5 each. Reported as issues #1539 and #1540 on 20 April 2026 and closed as completed on 24 July 2026. The file browser still starts at the container root by design. -1. https://github.com/agent0ai/agent-zero/issues/1540 2026-09-09. Two flaws recorded in the project's own security-review ledger and fixed in v2.12 the same day. An unauthenticated Telegram webhook accepted forged updates, and WhatsApp document names could overwrite files outside the media cache before the sender check ran. The ledger rates both high. Named in the release notes, with no advisory. -2. https://github.com/agent0ai/agent-zero/blob/main/security-review/LEDGER.md | -6 | | **Total** | | | | **54.2 → C** | ### Why each score - Reliability 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 191 test files, and its only two workflows publish Docker images and close inactive issues, so no public CI run shows the tests passing (5 of 25). 139 open issues and pull requests on 12 October 2026. 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). v2.13, past 1.0 (15). - Performance: Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes. - Schema & documentation 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). - Agent ergonomics 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). - Security & auth 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 hash of the instance id to api.agent-zero.ai, and one setting turns it off. The reviewed docs do not describe what it sends (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, security.txt answered 404, and the repository has no published advisory, while NVD lists five CVEs since March 2026. A security-review ledger in the repository records two findings, and the v2.12 notes name both fixes (6). - Payments & pricing 60: 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. - Task success: Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored. - Maintenance & community 75: v2.13 was published on 23 September 2026, 19 days before this check (30). Nine releases since 14 July 2026, v2.5 to v2.13 (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 (10 of 25). The Docker image, the desktop Launcher, the install scripts and the A0 CLI connector come from the same organisation, and the README links Launcher 1.8 (10 of 15). A Docker publish workflow builds images from tags, and the v2.0 notes record a LiteLLM upgrade past a patched CVE floor. No public test CI (5 of 10). - Transparency & trust 55: 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 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). No telemetry was found, and the update check has an off switch in settings, but what it sends is not described in the reviewed docs (10 of 20). Fix list for a coding agent, everything this grade says the listing lacks, the biggest gain first (26 items): https://www.anchorterminal.com/fixes/agent-zero.md (JSON https://www.anchorterminal.com/fixes/agent-zero.json) ### What we couldn't check - Fit. Agent Zero's README calls it an open agent framework and a Linux workbench, and its use cases are software, research and office files. It is a general agent framework with messaging channels, a scheduler and memory, not a product built as a personal assistant. It has no built-in calendar or contacts connection - Kind. Recorded as `harness`, the closest kind the briefs define for an agent program the owner runs, with `metrics.kind` local - `assistant.accounts` is claimed only for the mailbox the email integration signs in to with a username and password. Anything else is reached through MCP servers or stored secrets - unchecked: whether CVE-2026-4307 is fixed, and the release date of 1.15, which the shallow clone and the 15 releases read do not cover - unchecked: the private report GHSA-q4mh-57gh-36r2 that issue #1609 cites. The repository's advisory list is empty, so its outcome is unknown - unchecked: the Docker image registry page, so image tags, architectures and pull counts are unconfirmed - unchecked: whether the tests pass today. No public CI runs them - unchecked: the registration date of agent-zero.ai, the MCP registry, the Launcher, installer and A0 CLI repositories, and the site's docs pages other than secrets - unchecked: where the Telegram, WhatsApp and email settings are encrypted, if anywhere. The source stores plugin settings as `config.json` and secrets as `secrets.env` under `/a0/usr` - The GitHub API reports the licence as NOASSERTION because the file adds contact lines. Its text is the MIT licence - The repository's last push was 11 October 2026, while main's last commit is 23 September, so current work sits on other branches - Researched as a candidate for the personal assistants category and listed under agent harnesses, because its README calls it an agent framework and Linux workbench and its messaging channels, scheduler and memory are plugins. ### Sources - repository README, read from a clone of main at e3051fb (23 September 2026): (seen 2026-10-12) - security-review ledger: (seen 2026-10-12) - Telegram integration README and defaults: (seen 2026-10-12) - WhatsApp integration README and defaults: (seen 2026-10-12) - email integration README and defaults: (seen 2026-10-12) - Infection Check README, defaults and its disabled toggle file: (seen 2026-10-12) - Tool Access README and defaults: (seen 2026-10-12) - memory plugin README and defaults: (seen 2026-10-12) - OAuth connections README and defaults: (seen 2026-10-12) - memory guide: (seen 2026-10-12) - usage guide (tasks, secrets, backups): (seen 2026-10-12) - connectivity and external API: (seen 2026-10-12) - MCP setup and configuration: (seen 2026-10-12) - A2A setup: (seen 2026-10-12) - VPS deployment guide (login variables): (seen 2026-10-12) - default settings and API token derivation: (seen 2026-10-12) - update check: (seen 2026-10-12) - API authentication decorators: (seen 2026-10-12) - model provider list: (seen 2026-10-12) - workflows: (seen 2026-10-12) - repository record (stars, open issues, licence): (seen 2026-10-12) - releases and release notes: (seen 2026-10-12) - published security advisories (none): (seen 2026-10-12) - 40 newest open issues and pull requests: (seen 2026-10-12) - issues #1539, #1540 and #1609: (seen 2026-10-12) - NVD record for CVE-2026-4308: (seen 2026-10-12) - NVD keyword search for agent-zero in three date windows from 12 October 2025 to 4 October 2026 (five CVEs). The link is the second window: (seen 2026-10-12) - vendor home page (legal entity, cookie notice, token): (seen 2026-10-12) - llms.txt: (seen 2026-10-12) - community platform terms: (seen 2026-10-12) - LLM API dashboard, about page: (seen 2026-10-12) - secrets docs page: (seen 2026-10-12) - security.txt (404) and robots.txt (404): (seen 2026-10-12) ## Who's behind it (provenance 53/100, checked 2026-10-12) | Check | Finding | Points | | --- | --- | --- | | Legal entity named | Agent Zero, s.r.o. | 20/20 | | Domain age | agent-zero.ai, no registry record we could read | 0/15 | | Endpoint on the vendor's domain | no hosted endpoint | n/a | | Terms of service | nothing hosted, so the MIT licence stands in | 10/10 | | Privacy policy | nothing hosted, not scored | n/a | | Status page | not found | 0/10 | | Changelog | published | 10/10 | | security.txt | not found | 0/10 | The site footer names Agent Zero, s.r.o., ID no. 231 46 508, Nové sady 988/2, 602 00 Brno, Czech Republic, and the `LICENSE` file carries the same company's copyright. No terms or privacy policy for the software was found. The site's terms page covers its community platform and its cookie page covers the website, so neither is linked here and the MIT licence stands in. `/.well-known/security.txt` on www.agent-zero.ai answered 404 on 12 October 2026, and the repository has no SECURITY.md. robots.txt on www.agent-zero.ai answered 404, read as no rules. agent-zero.ai redirects to www.agent-zero.ai. There is no hosted endpoint. An instance answers on its owner's own host. The domain's registration date was not looked up. ### Terms and privacy, as read A reading by a fixed set of rules, each answered with the vendor's own sentence. Not legal advice. **Terms of service**. Nothing is hosted by the vendor, so there are no terms of service to read. The MIT licence stands in and the check scores in full. **Privacy policy**. Nothing is hosted by the vendor, so there is no privacy policy to read and the check isn't scored. ## Probe metrics Not measured yet. Our benchmark probes haven't run, so there's no availability, latency or error rate from a run and Performance is pending. Live uptime, where we poll the endpoint, is under Live and doesn't change the score. ## Strengths - MIT licence, with prompts, tools, plugins and settings readable and editable in one public repository - Nine tagged releases between 17 July and 23 September 2026, and Breaking Changes sections in the v2.11, v2.12 and v2.13 notes - Memory dashboard to search, edit, delete and bulk-delete entries, with memory kept apart for each project by default - No usage telemetry found in the source. The one call home is an update check that a setting turns off - Tool Access policy can allow or block each built-in and MCP tool for a project or an agent profile ## Weaknesses - No approval step before shell commands, file changes or outgoing messages. Tool Access defaults to allow - The web interface has no login until the owner sets a username, and the README command publishes port 80 - Five CVEs published between 17 March and 30 September 2026, none as a GitHub advisory, and no SECURITY.md or security.txt - Infection Check, the prompt-injection audit before tool calls, ships turned off - Empty allow-lists in the Telegram, WhatsApp and email integrations accept messages from anyone - No public CI runs the 191 test files. The only workflows publish Docker images and close inactive issues ## Before you call it (notes for agents) 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 ## Connect Install: ```bash docker run -p 80:80 -v a0_usr:/a0/usr agent0ai/agent-zero # or: curl -fsSL https://bash.agent-zero.ai | bash ``` ## Similar tools Ranked by shared capabilities, then score. Same-category tools with no shared capability key are listed last. | Tool | Grade | Score | Rank | Shared capabilities | x402 | Markdown | | --- | --- | --- | --- | --- | --- | --- | | Kilo Code CLI | BB | 75.4 | 48 | agent.harness, agent.mcp-client | no | https://www.anchorterminal.com/tools/kilo-code-cli.md | | goose | BB | 73.9 | 81 | agent.harness, agent.mcp-client | no | https://www.anchorterminal.com/tools/goose.md | | OpenAI Codex | BB | 73 | 95 | agent.harness, agent.mcp-client | no | https://www.anchorterminal.com/tools/openai-codex.md | | Qwen Code | BB | 72.4 | 107 | agent.harness, agent.mcp-client | no | https://www.anchorterminal.com/tools/qwen-code.md | | OpenHands | BB | 70.8 | 143 | agent.harness, agent.mcp-client | no | https://www.anchorterminal.com/tools/openhands.md | | Pi | B | 68.4 | 219 | agent.harness, agent.mcp-client | no | https://www.anchorterminal.com/tools/earendil-pi.md | ## Panel reviews (0) Reviewed by the Anchor panel (https://www.anchorterminal.com/reviewers/index.md): . Desk reviews, written from public documentation, pricing, terms, source and status history on 1 October 2026. No calls made. For a desk review, the outcome says whether the reviewer's questions could be answered from public material: success, partial or failure. How reviews work: https://www.anchorterminal.com/reviews/how-it-works.md ## Notable - The project's README describes it as an open agent framework and a Linux workbench. Messaging channels, the scheduler and memory are plugins and tools of that framework (source: ) - No approval step exists for shell commands, file changes or outgoing messages. The Tool Access policy defaults to allow for built-in and MCP tools (source: ) - The web interface has no login until `AUTH_LOGIN` is set, and the README's Docker command publishes port 80 (source: , ) - Infection Check, which has a second model audit the agent's reasoning for prompt injection before each tool call, ships with a `.toggle-0` file that disables it (source: ) - Telegram `allowed_users`, WhatsApp `allowed_numbers` and the email `sender_whitelist` accept every sender when empty. The email filter matches the claimed From address, not an authenticated identity (source: ) - v2.12 of 9 September 2026 fixed a Telegram webhook authentication bypass and a WhatsApp media path traversal, both found in the project's own review and recorded in a ledger (source: ) - NVD lists five CVEs published between 17 March and 30 September 2026 (CVE-2026-4307, CVE-2026-4308, CVE-2026-47119, CVE-2026-51852, CVE-2026-51853). The repository has published no GitHub advisory and has no SECURITY.md (source: ) - An update check, on by default, posts the version and a hashed instance id to api.agent-zero.ai. `update_check_enabled` turns it off. No other telemetry was found in the source (source: ) - Memory is a FAISS vector store under `/a0/usr/memory` or inside a project, written automatically from conversations by default, with a dashboard to search, edit and delete entries (source: ) - The API token for the external API, MCP server and A2A is 16 characters of a SHA-256 hash of the instance id, username and password, and A2A carries it in the URL path (source: ) - Agent Zero, s.r.o. of Brno, Czech Republic, is named on the site as the company behind the project. The site also runs a community platform around an A0T token on Base (source: ) - #19 of 21 in Best agent harnesses and coding agents: https://www.anchorterminal.com/best/agent-harnesses/index.md - All 205 harnesses comparisons: https://www.anchorterminal.com/compare/agent-harnesses/index.md ## Compare - [Agent Zero vs Aider](https://www.anchorterminal.com/compare/agent-zero-vs-aider.md): C 54.2 vs D 46.9 - [Agent Zero vs Amp](https://www.anchorterminal.com/compare/agent-zero-vs-amp.md): C 54.2 vs C 57.1 - [Agent Zero vs Antigravity CLI](https://www.anchorterminal.com/compare/agent-zero-vs-antigravity-cli.md): C 54.2 vs C 57.4 - [Agent Zero vs Claude Code](https://www.anchorterminal.com/compare/agent-zero-vs-claude-code.md): C 54.2 vs C 61.9 - [Agent Zero vs Cline](https://www.anchorterminal.com/compare/agent-zero-vs-cline.md): C 54.2 vs C 60.4 - [Agent Zero vs Cursor CLI](https://www.anchorterminal.com/compare/agent-zero-vs-cursor-cli.md): C 54.2 vs F 35.3 - [Agent Zero vs Devin](https://www.anchorterminal.com/compare/agent-zero-vs-devin.md): C 54.2 vs C 55.7 - [Agent Zero vs Droid CLI](https://www.anchorterminal.com/compare/agent-zero-vs-droid-cli.md): C 54.2 vs C 59.1 - [Agent Zero vs Pi](https://www.anchorterminal.com/compare/agent-zero-vs-earendil-pi.md): C 54.2 vs B 68.4 - [Agent Zero vs Gemini CLI](https://www.anchorterminal.com/compare/agent-zero-vs-gemini-cli.md): C 54.2 vs B 66.7 - [Agent Zero vs GitHub Copilot CLI](https://www.anchorterminal.com/compare/agent-zero-vs-github-copilot-cli.md): C 54.2 vs C 57.6 - [Agent Zero vs goose](https://www.anchorterminal.com/compare/agent-zero-vs-goose.md): C 54.2 vs BB 73.9 - [Agent Zero vs Kilo Code CLI](https://www.anchorterminal.com/compare/agent-zero-vs-kilo-code-cli.md): C 54.2 vs BB 75.4 - [Agent Zero vs Kiro CLI](https://www.anchorterminal.com/compare/agent-zero-vs-kiro-cli.md): C 54.2 vs C 59.9 - [Agent Zero vs OpenAI Codex](https://www.anchorterminal.com/compare/agent-zero-vs-openai-codex.md): C 54.2 vs BB 73 - [Agent Zero vs OpenCode](https://www.anchorterminal.com/compare/agent-zero-vs-opencode.md): C 54.2 vs B 67.7 - [Agent Zero vs OpenHands](https://www.anchorterminal.com/compare/agent-zero-vs-openhands.md): C 54.2 vs BB 70.8 - [Agent Zero vs Prime Agent](https://www.anchorterminal.com/compare/agent-zero-vs-prime-agent.md): C 54.2 vs C 60.5 - [Agent Zero vs Qwen Code](https://www.anchorterminal.com/compare/agent-zero-vs-qwen-code.md): C 54.2 vs BB 72.4 ## Verify this listing For the vendor. The badge or a plain link to this page verifies the listing, from a page on agent-zero.ai or one of its subdomains, or the README of github.com/agent0ai/agent-zero. It shows the listing is the vendor's and that the vendor knows it's here, and it never changes a grade, rank or review. The vendor sends the page's address to `POST https://www.anchorterminal.com/api/v1/verify` as `{"slug": "agent-zero", "url": "…"}`, or calls the `verify_listing` tool at https://www.anchorterminal.com/mcp. We fetch the page once, then again every week; two failed checks in a row and the verification lapses, and a later pass restores it. What we check: https://www.anchorterminal.com/builders/index.md#verify HTML badge: ```html Agent Zero on Anchor Terminal ``` Markdown badge, for a README: ```markdown [![Agent Zero on Anchor Terminal](https://www.anchorterminal.com/badges/agent-zero.svg)](https://www.anchorterminal.com/tools/agent-zero) ``` Plain link: ```html Agent Zero on Anchor Terminal ``` ## Share this listing For the vendor. Sharing assets for social media, two PNGs of 1200 × 630 that say Agent Zero is listed on Anchor Terminal, with the vendor's logo and this page's address and no grade or score. - Dark: https://www.anchorterminal.com/assets/share/agent-zero-dark.png - Light: https://www.anchorterminal.com/assets/share/agent-zero-light.png