Orca vs Mirror CLI

Orca 75

Tags to v1.4.251 and commits on 6 November 2026 (30). Many releases in 90 days (20). GitHub issues and pull requests weren't read (GitHub's pages refuse these sessions), so that line is scored absent (0). Current builds (15). Extensive CI (10). 30 + 20 + 0 + 15 + 10 = 75.

Mirror CLI 47

0.1.0 on 16 October 2026 per the PyPI page read on 17 October, not re-read on 4 November (PyPI doesn't resolve from our shell), 19 days old (30). The 90-day line needs three dated releases. 0.1.0 (16 October) and the mirror-agent-v0.1.8 tag on the same commit, f938033, are one release day, and 0.1.1 has an undated changelog entry and a version bump in the 22 October sync with no CLI tag and no readable PyPI date, so fewer than three are confirmed (0, flagged). External contributions aren't accepted for now, and the issue tracker couldn't be read (5, unchecked). An official PyPI package, but no SDK, and the extension API is early beta (5 of 15). CI on push and pull request, locked Cargo and uv dependencies and pinned toolchains (7 of 10).

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.

Mirror CLI 60

Self-hosted rule. No payment protocol (0). The CLI is free under Apache-2.0 with nothing to buy (20). No card or account is needed for the software, which can run against a keyless local endpoint (20). An agent can install and run it with no sign-up, given a model endpoint (20). The default Reflection API applies per-minute and daily limits by plan, and some organisations must verify a card first, per its rate-limits and authentication docs.

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.

Mirror CLI 40

Local-package reading. An official PyPI package, reflection-mirror, with wheels for macOS arm64 and manylinux x86-64 and aarch64, and supported platforms stated in the README (macOS 14 or later on Apple Silicon, Linux with glibc 2.28 or later, Python 3.12 or later) (20). A public CI workflow runs the Python package tests (ci.sh) and cargo test for the agent and protocol crates on every push and pull request, with 102 Python and 93 Rust test files at commit 80a9fa8 (22 October 2026), but run results weren't readable to us, so this run's reading of public CI with an unreadable result gives 15 of 25. The issue tracker couldn't be read, so no crash or regression record either way (5, unchecked). A CHANGELOG.md now lists 0.1.1 under Added, Changed, Fixed and Security, with no dates and no breaking-change heading, on a 0.x version (0, flagged). 0.1.x, labelled early beta in the docs (0).

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.

Mirror CLI 58

Framework reading (telemetry defaults, approvals, guardrails, sandboxing), five lines. Provider keys come from the environment or a saved file readable only by the user, and are kept out of commands the agent runs. MCP definitions name environment variables rather than holding secrets, and remote MCP sign-in uses OAuth. Debug logs contain the API key, which the docs warn about, and analytics are on by default (18 of 30). Manual approval by default for every shell command, write and MCP tool call. Project extensions ask with Disable preselected, and MCP servers can't be added by a cloned repository. Auto mode, once chosen, applies in every directory (15 of 20). SECURITY.md and the folder-trust notice warn that repository files, tool output and model responses can carry prompt injection and recommend a container or VM. The microVM sandbox is opt-in and covers file and shell tools only (9 of 15). Conversations with their tool calls are kept in ~/.mirror/state.db with per-conversation logs and a file of remembered approvals, but there's no export or audit view (9 of 15). SECURITY.md gives a private email and a report scope, but there's no security.txt, bug bounty or published advisory (7 of 20). Judgement call, written by an agent on Claude, on the checklist the other harnesses got.

Orca 70

Harness reading. An orchestrator agent that splits work across workers in their own workspaces, chat or raw CLI, a browser and a CLI in one app (70).

Mirror CLI 58

Framework reading, adapted to a harness driven by a pipeline. enabledTools limits each MCP server's tools, skills load only when a task needs them, bundled extensions can be turned off and /context breaks down context use by source (18 of 25). --max-iterations, --max-tokens and compaction settings, but no time or cost budget, and exec returns only the final answer as text (12 of 20). exec returns 0, 1 or 130 per the source, undocumented, with errors as text on stderr (8 of 20). Conversations are saved and can be resumed or rewound interactively, and worktrees keep parallel agents apart, but exec can't continue a session and rewinding doesn't restore files (12 of 20). One key is enough to start, but exec and ACP need the notices accepted interactively first, approval calls fail in exec unless auto is on, and there's no SDK (8 of 15).

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.

Mirror CLI 66

Apache-2.0, with NOTICE and third-party licences in the repository (30). The README and SECURITY.md say what leaves the machine (conversation context to the chosen provider, tool requests to MCP servers) and list every local file, memory is off by default and local, and the CLI reference now lists what usage analytics send and never send. Reflection's privacy policy is on reflection.ai, whose robots.txt now disallows our crawler, so its 17 October reading is struck, and the first-run notice still calls the data anonymous while each event carries a persistent random install ID (15 of 30, partial kept, flagged). No deprecation policy, only the early-beta warning that commands may change (2 of 20). Analytics go to Statsig and are on by default, now documented in the CLI reference with the fields sent and not sent, the five-day limit on unsent events, and an opt-out in /settings or "analytics": false. Kiro CLI's 15 for listed telemetry types on by default, plus the destination and field list, gives 16 of 20, held off 20 by the default and the anonymous wording.