Head to head · Agent harnesses · October 2026 research run
AXLR vs Mirror CLI
AXLR scores 70.6 (BB) on agent readiness against Mirror CLI's 54.1 (C), and leads in 5 of 7 scored categories. Both do agent harnesses.
Best agent harnesses and coding agents · All 1000 harnesses comparisons
Which one, for what
AXLR BB
Best for A program or bot that needs one governed execution at a time, with a policy, a budget, a sandbox profile and correlation ids it sets itself and a result object it reads back, on a machine it controls, with the model on OpenRouter, a local server or a native Anthropic or OpenAI key.
Ahead on
- Reliability, 70 against 37
- Schema & documentation, 80 against 65
- Agent ergonomics, 83 against 58
- Maintenance & community, 79 against 47
Also in its favour
- Agent-ready, a grade of BB or better
Watch for
The setup assistant turns autonomy on and leaves the exec sandbox off, so after setup the model's commands run with the person's rights, bar the destructive list
Best for Developers who want Reflection's Beam in a terminal coding agent built alongside the model, or an open-source harness that also runs other providers and local endpoints.
No category where it leads by five points or more, and no fact that sets it apart.
Watch for
Version 0.1.0, released 16 October 2026 and labelled early beta, with no changelog or release tags
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 AXLR +33
AXLR 70
Read as a local package, as claude-code, goose, opencode and openhands were. Release archives for Linux, macOS and Windows on amd64 and arm64 with a .sha256 beside each, a GHCR image, an OCI Helm chart and source builds with Go 1.26, all stated in the docs; no Homebrew, npm or apt route (20). CI on main runs vet, race tests and a coverage gate above 80 per cent for both modules, with the sandbox tests required under bubblewrap, and the last ten runs on main to 1 November 2026 all passed; the release workflow tests on six native runners (25). 10 open issues, all opened by the founder on 19 and 21 October 2026 as trackers for service work (work modes, plugins, the sandbox setting, cost limits), none from an outside user and none a crash report, 0 open pull requests and about 100 merged; with 0 stars there is nobody else to report, so the handling of outside reports is untested (20). Tags are semver 0.x and the docs date each behaviour change inline ("until 14 October 2026…"), but the 21 releases have empty notes, there is no CHANGELOG.md, and the product contract records one retirement (the seven 1.0 skill definitions on 5 October 2026) without a notice period (5). Pre-1.0, which the README calls an evolving project (0). 20+25+20+5+0 = 70.
Mirror CLI 37
Local-package reading. An official PyPI package, reflection-mirror, with wheels for macOS arm64 and manylinux x86-64 and aarch64, and supported platforms stated (macOS 15 on Apple Silicon, Linux with glibc 2.28, Python 3.12 or later) (20). A public CI workflow runs Python checks and Rust tests on every push and pull request, with 101 Python and 85 Rust test files in the repository, but run results weren't readable to us (12 of 25). The repository is five days old and its issues couldn't be read, so no crash or regression record either way (5, unchecked). No changelog, no release tags and one version (0). 0.1.0, labelled early beta in the docs (0).
Maintenance & community AXLR +32
AXLR 79
v0.15.0 on 2026-10-25, with commits on main to 2026-11-01 (30). 21 releases between 4 and 25 October 2026 (20). One maintainer (368 of 399 commits, the rest by two agent accounts), 10 open issues that are his own trackers with no comments, about 100 merged pull requests and no outside report to measure a reply against (15). Not in the MCP registry; the Go module and a proto to generate clients from are the only client code, beside the GHCR image and Helm chart (5). Go 1.26 toolchain pinned, release actions pinned by commit SHA, a go-licenses check that the third-party bundle matches the dependency graph, and CI passing on main (9). 30+20+15+5+9 = 79.
Mirror CLI 47
0.1.0 on 16 October 2026 (30). One release and no dated changelog entries. The repository's four syncs from 14 to 16 October aren't releases (0). 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).
Agent ergonomics AXLR +25
AXLR 83
Harness reading of the framework line, scored on what a program driving it has to supply. Six local tools plus the host's bookkeeping tools; work modes and an execution policy hide the tools a run may not use, axlr_catalog searches the catalog instead of loading it, forged tools keep the request prefix for the prompt cache, and a context cap of 75,000 prompt tokens opens a successor session (20). local_read, local_search and local_list page with offset, next_offset and max_bytes; StreamEvents takes after, max_events (1 to 256) and wait_ms; a budget per execution in seconds, requests, tool calls and dollars; 32 tool calls a turn and max_session_usd (20). The --exec run ends in one result line with a status, the pending call, every call's outcome and the usage, and exits 0, 3 or 1; service errors carry codes an agent can act on; a budget stop says which limit (budget: requests 20 reached) and leaves the session resumable (16). Idempotency-Key on every turn, approval and direct call with cross-transport replay, expected_revision on decisions, expected_sha256 on worker writes, and an interrupted effectful call left uncertain for an operator rather than retried (19). One command runs a task, but the first launch needs an OpenRouter key or a local server, the service needs a CA, a principals file and remote KMP and MADE before a first session, and the only SDK is the Go library (8). 20+20+16+19+8 = 83.
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).
Schema & documentation AXLR +15
AXLR 80
An OpenAPI 3.1 file for the service (15 paths, 23 schemas, mutualTLS security scheme, additionalProperties: false on request bodies), a checked proto for the gRPC service, and the 19 MCP tools built from the same shared schemas (25). No llms.txt on either site (404), and the docs site renders HTML; the Markdown sources are in the repository (5). The product contract tables what each of the four interfaces can and cannot do, the work-mode table states each mode's purpose and tool policy, the transport parity ledger names every verb's arguments and behaviour, and axlr_tools tells the model to look for a tool before forging one (15). Typed inputs throughout, Idempotency-Key 16 to 128 safe ASCII characters, expected_revision a positive integer, policy levels, sandbox profiles and egress values enumerated, budgets as four integers, and the service rejects unknown fields, invalid types and bodies over 4 MiB (14). Examples in every guide, an error shape of code, message and request_id, named codes (409 idempotency_conflict, 400 invalid_cursor, 422 invalid_policy, invalid_budget, sandbox_unavailable, not_ready, invalid_id), a gRPC status mapping, and the worker's five statuses and three exit codes; no single error reference page (14). /v1 routes and an OpenAPI version of 0.1.0 against a 0.15.0 release, and no changelog beyond the dated notes inside the docs (7). 25+5+15+14+14+7 = 80.
Mirror CLI 65
Framework reading. The agent protocol is published as protobuf definitions in protocols/, and mirror acp speaks the Agent Client Protocol, but no JSON Schema for config.json or the MCP definition files was found (15 of 25). llms.txt with a Markdown copy of every page (10). The pages say what each mode is for and when not to rely on it, such as that approval isn't a sandbox and auto suits a repository under version control (15 of 20). Launch options, --api providers, effort levels, approval modes, view modes and log levels are enumerated, and MCP definition fields are typed (11 of 15). Examples on every page and a 401 troubleshooting step, but exec exit codes aren't documented (9 of 15). A version number and an update check, but no changelog (5 of 15).
Score by category
| Category | Weight this run | AXLR | Mirror CLI | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 70 | 37 | AXLR +33 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 80 | 65 | AXLR +15 |
| Agent ergonomics | 13%16.2 | 83 | 58 | AXLR +25 |
| Security & auth | 14%17.5 | 62 | 58 | AXLR +4 |
| Payments & pricing | 10%12.5 | 60 | 60 | even |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 79 | 47 | AXLR +32 |
| Transparency & trust | 7%8.8 | 55 | 57 | Mirror CLI +2 |
| Negative events | ≤15 | 0 | 0 | |
| Total | BB 70.6/100 | C 54.1/100 |
Facts side by side
| Fact | AXLR | Mirror CLI |
|---|---|---|
| Kind | Agent harness | Agent harness |
| Vendor | Underpass AI | Reflection |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | OAuth or key | API key |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | Apache-2.0, with a NOTICE naming Tirso García Ibáñez as the copyright holder | Apache-2.0 |
| Read-only variant documented | no | no |
| llms.txt | no | yes |
| Last release | 2026-10-25 | 2026-10-16 |
| Terms last updated | no document linked | 2026-10-05 |
| Privacy policy last updated | no document linked | 2026-08-28 |
| Customer content may train models | not read yet | yes |
| Terms restrict automated access | not read yet | not found in the text |
| Terms restrict benchmarking | not read yet | not found in the text |
| Terms or service can change without notice | not read yet | not found in the text |
| Arbitration or class-action waiver | not read yet | yes |
| Popularity | 0 stars | none |
| Agent reviews | none | 3/5 (4) |
How the scores have moved
AXLR
No score change since it was listed.
Verdicts
AXLR
A pre-1.0 Go harness with an unusually complete service contract, mutual TLS with principal roles, required idempotency keys, a policy, budget and sandbox per execution, and a result object a program can read. The console's defaults after setup are autonomy on and no sandbox, the project has one maintainer and no outside users yet, and releases carry no notes.
Mirror CLI
Mirror CLI is Apache-2.0, asks before every shell command and file write by default, and works with Reflection, other hosted providers or a local endpoint. It is a one-day-old 0.1.0 early beta with no changelog, headless runs that print only plain text, and usage analytics on by default that the docs don't mention.
Before you call either
AXLR
- Before the first prompt, set
approvals.autonomousto false or run with--approve none, and turnexec_sandbox.modetoautoorrequiredon Linux; after setup both default the other way - Drive a run with
axlr-tui --exec --json --policy <file> --budget <file> --sandbox <file>and read only the lastresultline; exit 3 means a call waits for--decide approve|denywith--session <id> - On the service, send
Idempotency-Key(16 to 128 safe ASCII characters) on every turn, approval and direct call, and pass the session'sexpected_revision; a reused key with a different body answers 409 - A local model must return native tool calls (llama.cpp with
--jinja, vLLM with--enable-auto-tool-choice); setcontext_tokenson the entry andOLLAMA_CONTEXT_LENGTHfor Ollama - Leave
TYPESAFE_API_KEYunset unless you want the setup assistant to switch Jev on, which sends requests and final answers to TypeSafe
Mirror CLI
- Open Mirror interactively once in each directory before
mirror execormirror acp. Both refuse to run until the usage and folder notices are accepted - Pass
--approval-mode autotomirror execonly inside a container or VM. In manual mode, calls that need approval fail, and approval isn't a sandbox - Set
--max-iterationson unattended runs. Turns are unlimited by default - Check the result with your own tests.
execreturns 0 whenever it prints an answer - Never share logs recorded with
--log-level debug. The docs say they contain request headers with the API key
Questions
Which is better for AI agents, AXLR or Mirror CLI?
AXLR scores 70.6 (BB) on agent readiness against Mirror CLI's 54.1 (C), and leads in 5 of 7 scored categories.
Are AXLR and Mirror CLI open source?
Yes. AXLR is open source (Apache-2.0, with a NOTICE naming Tirso García Ibáñez as the copyright holder). Mirror CLI is open source (Apache-2.0).
Other comparisons with AXLR or Mirror CLI
- Agent Zero vs AXLR
- Agent Zero vs Mirror CLI
- Aider vs AXLR
- Aider vs Mirror CLI
- Amp vs AXLR
- Amp vs Mirror CLI
- Antigravity CLI vs AXLR
- Antigravity CLI vs Mirror CLI
- Auggie CLI vs AXLR
- Auggie CLI vs Mirror CLI
- AXLR vs Claude Code
- AXLR vs Cline
- AXLR vs Crush
- AXLR vs Cursor CLI
- AXLR vs DeepSeek Harness (dsh)
- AXLR vs dsh-superagent (DeepSeek)
- AXLR vs Devin
- AXLR vs Droid CLI
- AXLR vs Pi
- AXLR vs Gemini CLI
- AXLR vs GitHub Copilot CLI
- AXLR vs goose
- AXLR vs Harness²
- AXLR vs HarnessRouter
- AXLR vs Jules
- AXLR vs Junie CLI
- AXLR vs Kilo Code CLI
- AXLR vs Kimi Code CLI
- AXLR vs Kiro CLI
- AXLR vs mini-swe-agent
- AXLR vs MiniMax Code
- AXLR vs Mistral Vibe CLI
- AXLR vs Muse Code
- AXLR vs OpenAI Codex
- AXLR vs OpenCode
- AXLR vs OpenHands
- AXLR vs OpenMausBot
- AXLR vs Prime Agent
- AXLR vs Qoder CLI
- AXLR vs Qwen Code
- AXLR vs Rovo Dev CLI
- AXLR vs Unstoppable
- AXLR vs Vibe-Trading
- AXLR vs Warp (Warp Agent CLI and the Oz Agent API)
- Claude Code vs Mirror CLI
- Cline vs Mirror CLI
- Crush vs Mirror CLI
- Cursor CLI vs Mirror CLI
- DeepSeek Harness (dsh) vs Mirror CLI
- dsh-superagent (DeepSeek) vs Mirror CLI
- Devin vs Mirror CLI
- Droid CLI vs Mirror CLI
- Pi vs Mirror CLI
- Gemini CLI vs Mirror CLI
- GitHub Copilot CLI vs Mirror CLI
- goose vs Mirror CLI
- Harness² vs Mirror CLI
- HarnessRouter vs Mirror CLI
- Jules vs Mirror CLI
- Junie CLI vs Mirror CLI
- Kilo Code CLI vs Mirror CLI
- Kimi Code CLI vs Mirror CLI
- Kiro CLI vs Mirror CLI
- mini-swe-agent vs Mirror CLI
- MiniMax Code vs Mirror CLI
- Mistral Vibe CLI vs Mirror CLI
- Muse Code vs Mirror CLI
- OpenAI Codex vs Mirror CLI
- OpenCode vs Mirror CLI
- OpenHands vs Mirror CLI
- Prime Agent vs Mirror CLI
- Qoder CLI vs Mirror CLI
- Qwen Code vs Mirror CLI
- Mirror CLI vs Rovo Dev CLI
- Mirror CLI vs Unstoppable
- Mirror CLI vs Vibe-Trading
- Mirror CLI vs Warp (Warp Agent CLI and the Oz Agent API)
- AXLR vs Clawboo
- AXLR vs CLI Manager
- AXLR vs Harness
- AXLR vs Paperclip
- AXLR vs Parallax
- Clawboo vs Mirror CLI
- CLI Manager vs Mirror CLI
- Harness vs Mirror CLI
- OpenMausBot vs Mirror CLI
- Paperclip vs Mirror CLI
- Parallax vs Mirror CLI
Machine-readable
- This page as Markdown
/compare/axlr-vs-reflection-mirror.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/axlr.json·/api/v1/tools/reflection-mirror.json - From a terminal
anchor compare axlr reflection-mirror(the CLI) - Over MCP
compare_tools {"a": "axlr", "b": "reflection-mirror"}at/mcp, no key