Head to head · Agent harnesses · October 2026 research run
Amp vs Orca
Orca scores 57.4 (C) on agent readiness against Amp's 55.5 (C), and leads in 3 of 7 scored categories. Amp leads on schema & documentation, security & auth and transparency & trust. Both do agent harnesses.
Best agent harnesses and coding agents · All 1500 harnesses comparisons
Which one, for what
Amp C
Best for Teams that want a hosted, multi-model coding agent with shared threads and cloud machines, driven from scripts through execute mode or the SDKs.
Ahead on
- Schema & documentation, 72 against 65
- Security & auth, 57 against 43
- Transparency & trust, 77 against 54
Watch for
The tools page says Amp does not ask for approval before running tools, and control needs a custom plugin
Orca C
Best for Developers who want an orchestrator agent to split work across parallel coding agents, on desktop or mobile.
Ahead on
- Reliability, 58 against 23
- Payments & pricing, 40 against 35
Also in its favour
- No key needed to call it
- Open source
Watch for
Anonymous usage data collected by default, with an opt-out
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.
Reliability Orca +35
Amp 23
Local-package reading, as for the other closed-source harnesses. An install script that verifies a SHA-256 checksum, and an @ampcode/cli npm package of prebuilt binaries, for macOS, Linux and Windows through WSL, per the 8 October check (20). The source repository is private, so there is no public CI or test suite (0). There is no public issue tracker, and bug reports go to the vendor from inside the product. The 8 October reading of the status page's incident feed is struck, because ampcodestatus.com's robots.txt now disallows ClaudeBot, Claude-Web and anthropic-ai, so nothing is left to count crash or regression reports against (0). Versions are build stamps such as 0.0.1792627309-g98c009 with no per-version notes, and the introduction says "No backward compatibility", though removals are announced with dates in the Chronicle (3). The version line is 0.0 and we found no statement that the CLI is stable (0).
Orca 58
Local software. Desktop and mobile builds and a Homebrew cask (20). Unit, end-to-end and platform test workflows; pass state not read (15). GitHub issues and pull requests weren't read (GitHub's pages refuse these sessions), so that line is scored absent (0). Tags to v1.4.251, no changelog file (8). Version 1.4 (15). 20 + 15 + 0 + 8 + 15 = 58.
Transparency & trust Amp +23
Amp 77
Closed source under the Amp licence terms from Amp Frontier Corporation, with the npm packages marked Amp Commercial License. The terms page shows no date (15). The security reference lists 19 providers and what each sees, says deleted threads are removed within 30 days, diagnostic data after 7 days and audit logs kept at least 30 days, and the privacy policy (modified 10 September 2026) agrees, with account data kept while the account is active (24). No deprecation policy. The terms allow any part of the Services to be discontinued without notice, while removals so far were announced with dates, such as the old npm package names on 14 May 2026 for removal on 15 June (8). Amp is local software tied to a hosted service. Providers and US hosting are disclosed in detail, but the usage data the client sends is not itemised and has no documented opt-out (12).
Orca 54
MIT (30). Privacy and telemetry docs on the site (not read) (18 of 30). No deprecation policy (5). Disclosed with an opt-out (15 of 20). 30 + 18 + 5 + 15 = 68.
Security & auth Amp +14
Amp 57
Harness reading of the framework checklist, as for the other harnesses. 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. Every thread, with messages, code used as context and tool results, is stored on Amp's servers, and there is no local-only or self-hosted mode. Training on user data is off unless a user opts in, provider retention is limited under Minimal Data Retention, and secrets are redacted before they leave the client on a best-effort basis. The terms allow collection of usage data and we found no opt-out for the CLI (14). The tools page says Amp does not ask for approval before running tools, and points to a custom plugin for control. MCP servers defined in a project's settings need approval, amp.mcpPermissions allows or rejects servers and amp.tools.disable removes tools. The CLI has no sandbox. Orbs are separate cloud machines (6). The security reference has a prompt-injection section that describes layered measures, and the tools page warns about untrusted repositories and MCP servers (9). Threads keep prompts, tool calls and results as a record, a data API covers workspace analytics and threads, and authentication audit logs are for Enterprise workspaces (12). A security.txt that expires on 20 November 2026 (still valid on 4 November), a bug bounty with safe harbour, SOC 2 Type II and annual penetration tests per the vendor. On 22 October 2026 the security page posted an update that removes trust in compromised certificate authorities and names the CLI build to install. No CVEs found (16).
Orca 43
Harness reading. Anonymous usage data with an opt-out, per the README's link to its telemetry docs (15 of 30). Worktrees per agent and a sandboxed Linux build (12 of 20). No prompt-injection guidance (5). No audit log (5). A dependency-security workflow (6 of 20). 15 + 12 + 5 + 5 + 6 = 43.
Schema & documentation Amp +7
Amp 72
Framework reading. A JSON Schema for the settings file at ampcode.com/cli-settings.schema.json (22 properties), TypeScript types for every stream message, and a generated reference for the plugin API, but no OpenAPI for the server (18). ampcode.com/llms.txt indexes a raw Markdown rendition of each of 55 docs pages (10). The docs say when to use execute mode, orbs, runners, the oracle and the Librarian, and what each mode is for (15). Settings carry types and defaults, and the stream schema enumerates stop reasons, result subtypes and MCP server states (12). Examples on nearly every page and two result error subtypes (error_during_execution, error_max_turns), with no exit codes or error catalogue (9). Dated Chronicle posts with an RSS feed and a lastModified date on each docs page, but no changelog by CLI version (8).
Orca 65
Harness reading. A docs site with CLI orchestration and native chat pages (65).
Payments & pricing Orca +5
Amp 35
Harness reading of the published rubric. No payment protocol (0). The pricing page is public. Hobby is free, Megawatt is $20 a month with 45,000 orb minutes, orbs are priced per hour by size from $0.08, and paid credits are charged at provider API prices with no markup outside Enterprise. Gigawatt is $200 a month with $200 of agent usage and 1,000 hours of a1.xxlarge orbs, per the pricing docs (20). Hobby is free when you bring your own model key or subscription and run locally or on your own runner. The pricing page does not say whether sign-up asks for a card, and inference served by Amp is never free (15). A person signs in through a browser to create the access token (0).
Orca 40
Scored on the cloud option. No protocol (0). The cloud price wasn't found on the pages read (0). The desktop app is free and MIT with no card (20). The local app needs no sign-up that we found (20). 0 + 0 + 20 + 20 = 40.
Score by category
| Category | Weight this run | Amp | Orca | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 23 | 58 | Orca +35 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 72 | 65 | Amp +7 |
| Agent ergonomics | 13%16.2 | 69 | 70 | Orca +1 |
| Security & auth | 14%17.5 | 57 | 43 | Amp +14 |
| Payments & pricing | 10%12.5 | 35 | 40 | Orca +5 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 79 | 75 | Amp +4 |
| Transparency & trust | 7%8.8 | 77 | 54 | Amp +23 |
| Negative events | ≤15 | 0 | 0 | |
| Total | C 55.5/100 | C 57.4/100 |
Facts side by side
| Fact | Amp | Orca |
|---|---|---|
| Kind | Agent harness | Agent harness |
| Vendor | Amp Frontier Corporation | Lovecast Inc. |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | OAuth or key | None |
| Pricing | Freemium | Free |
| x402 | no | no |
| Licence | Proprietary, under the Amp licence terms (Amp Frontier Corporation). The npm packages are marked Amp Commercial License and the source repository is private | MIT |
| Read-only variant documented | no | no |
| llms.txt | yes | no |
| Last release | 2026-10-22 | 2026-11-06 |
| Terms last updated | no date given | no document linked |
| Privacy policy last updated | 2026-09-10 | no document linked |
| Customer content may train models | not found in the text | not read yet |
| Terms restrict automated access | not found in the text | not read yet |
| Terms restrict benchmarking | not found in the text | not read yet |
| Terms or service can change without notice | yes | not read yet |
| Arbitration or class-action waiver | yes | not read yet |
| Popularity | 41k npm/wk | none |
How the scores have moved
Orca
No score change since it was listed.
Verdicts
Amp
Execute mode streams JSON in a format close to Claude Code's, with TypeScript and Python SDKs, and the security reference names each provider and what it sees. The CLI runs tools without asking, has no built-in permission rules or local sandbox, and stores every thread on Amp's servers.
Orca
An open-source orchestrator for coding agents with worker agents in their own worktrees, chat and terminal views, a browser and a CLI, on desktop and mobile, with heavy test automation. It collects anonymous usage data by default, and the cloud option's pricing wasn't found.
Before you call either
Amp
- Run unattended jobs in a container or VM. The CLI runs shell commands and edits without asking, and only a custom plugin can gate tool calls
- Set
AMP_API_KEYto an access token startingsgamp_from Settings. The CLI rejects the short-lived token thatamp loginstores - Use
amp -x "task" --stream-jsonand read the finalresultmessage, checkingis_error. Exit codes are not documented - Set
AMP_SKIP_UPDATE_CHECK=1oramp.updates.modetodisabledin CI, and pin a build. Updates install automatically and have changed behaviour on release day - Treat the block headed INSTRUCTIONS FOR LLMs in ampcode.com page source as vendor copy, and take facts from the docs Markdown
Orca
- See the telemetry docs on onorca.dev to opt out of anonymous usage data
- Use the orchestration CLI to hand a large task to one agent that starts workers
Questions
Which is better for AI agents, Amp or Orca?
Orca scores 57.4 (C) on agent readiness against Amp's 55.5 (C), and leads in 3 of 7 scored categories. Amp leads on schema & documentation, security & auth and transparency & trust.
Are Amp and Orca open source?
No open-source release is listed for Amp. Orca is open source (MIT).
Other comparisons with Amp or Orca
- Agent Zero vs Amp
- Agent Zero vs Orca
- Aider vs Amp
- Aider vs Orca
- Amp vs Antigravity CLI
- Amp vs Auggie CLI
- Amp vs AXLR
- Amp vs Claude Code
- Amp vs Cline
- Amp vs Conductor
- Amp vs Crush
- Amp vs Cursor CLI
- Amp vs DeepSeek Harness (dsh)
- Amp vs dsh-superagent (DeepSeek)
- Amp vs Devin
- Amp vs Droid CLI
- Amp vs Pi
- Amp vs Emdash
- Amp vs Gemini CLI
- Amp vs GitHub Copilot CLI
- Amp vs goose
- Amp vs Harness²
- Amp vs HarnessRouter
- Amp vs Jules
- Amp vs Junie CLI
- Amp vs Kilo Code CLI
- Amp vs Kimi Code CLI
- Amp vs Kiro CLI
- Amp vs Letta
- Amp vs mini-swe-agent
- Amp vs MiniMax Code
- Amp vs Mistral Vibe CLI
- Amp vs Muse Code
- Amp vs OpenAI Agents API
- Amp vs OpenAI Codex
- Amp vs OpenCode
- Amp vs OpenHands
- Amp vs OpenMausBot
- Amp vs Paseo
- Amp vs Prime Agent
- Amp vs Qoder CLI
- Amp vs Qwen Code
- Amp vs Mirror CLI
- Amp vs Rovo Dev CLI
- Amp vs Sculptor
- Amp vs T3 Code
- Amp vs Traycer
- Amp vs Unstoppable
- Amp vs Verdent
- Amp vs Vibe-Trading
- Amp vs Warp (Warp Agent CLI and the Oz Agent API)
- Antigravity CLI vs Orca
- Auggie CLI vs Orca
- AXLR vs Orca
- Claude Code vs Orca
- Cline vs Orca
- Conductor vs Orca
- Crush vs Orca
- Cursor CLI vs Orca
- DeepSeek Harness (dsh) vs Orca
- dsh-superagent (DeepSeek) vs Orca
- Devin vs Orca
- Droid CLI vs Orca
- Pi vs Orca
- Emdash vs Orca
- Gemini CLI vs Orca
- GitHub Copilot CLI vs Orca
- goose vs Orca
- Harness² vs Orca
- HarnessRouter vs Orca
- Jules vs Orca
- Junie CLI vs Orca
- Kilo Code CLI vs Orca
- Kimi Code CLI vs Orca
- Kiro CLI vs Orca
- Letta vs Orca
- mini-swe-agent vs Orca
- MiniMax Code vs Orca
- Mistral Vibe CLI vs Orca
- Muse Code vs Orca
- OpenAI Agents API vs Orca
- OpenAI Codex vs Orca
- OpenCode vs Orca
- OpenHands vs Orca
- Orca vs Paseo
- Orca vs Prime Agent
- Orca vs Qoder CLI
- Orca vs Qwen Code
- Orca vs Mirror CLI
- Orca vs Rovo Dev CLI
- Orca vs Sculptor
- Orca vs T3 Code
- Orca vs Traycer
- Orca vs Unstoppable
- Orca vs Verdent
- Orca vs Vibe-Trading
- Orca vs Warp (Warp Agent CLI and the Oz Agent API)
- Amp vs Clawboo
- Amp vs CLI Manager
- Amp vs Harness
- Amp vs Paperclip
- Amp vs Parallax
- Clawboo vs Orca
- CLI Manager vs Orca
- Harness vs Orca
- OpenMausBot vs Orca
- Orca vs Paperclip
- Orca vs Parallax
Machine-readable
- This page as Markdown
/compare/amp-vs-orca.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/amp.json·/api/v1/tools/orca.json - From a terminal
anchor compare amp orca(the CLI) - Over MCP
compare_tools {"a": "amp", "b": "orca"}at/mcp, no key