Head to head · Agent harnesses · October 2026 research run
AXLR vs Pi
AXLR scores 70.6 (BB) on agent readiness against Pi's 62.6 (B), and leads in 2 of 7 scored categories. Pi leads on reliability, maintenance & community and transparency & trust. 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
- Agent ergonomics, 83 against 76
Also in its favour
- Agent-ready, a grade of BB or better
- No incidents deducted, where Pi loses 10 points for them
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
Pi B
Best for Developers and pipelines that want a small, scriptable coding agent they can extend in TypeScript and drive over JSONL or RPC, inside their own container.
Ahead on
- Reliability, 75 against 70
- Maintenance & community, 87 against 79
- Transparency & trust, 67 against 55
Also in its favour
- No key needed to call it
Watch for
No permission system or sandbox. Tool calls run with the user's rights and without an approval prompt
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.
Transparency & trust Pi +12
AXLR 55
Apache-2.0 with a NOTICE (30). No privacy policy or terms on underpassai.com or axlr.underpassai.com; the docs' 'Where data goes' and 'Diagnostics and privacy' sections say that model requests go to OpenRouter, the local server or the native API, that Jev sends text to TypeSafe only when on, that sessions live under $XDG_STATE_HOME/axlr, that payload capture is off by default and redacted when on, and that traces are deleted after 30 days; nothing covers the engine downloads' or the catalog registry's handling of a client's requests (15). No deprecation policy; pre-1.0 changes are dated inline in the docs and the product contract records the 5 October 2026 retirement of the first skill catalogue after the fact (6). No telemetry to disclose, and the docs say in two places what leaves the machine and how to stop payload capture, though no single page says there is no telemetry (17). 30+15+6+17 = 68.
Pi 67
MIT (30). No privacy policy for pi.dev or the CLI was found (pi.dev/privacy, earendil.com/privacy and radius.earendil.com/privacy return 404 on 23 October 2026, and pi.dev/privacy and pi.dev/terms again on 1 November). The docs say where sessions and credentials are stored and what /share and /bug upload. The Radius alpha terms of 1 September 2026 name Earendil Works Co. and refer to a Privacy Notice we couldn't locate (10). Breaking changes are listed per release with migration steps, with no deprecation policy or notice period found. Pi Durable's README says its API changes without notice between releases (8). Install telemetry and the version check are documented in the settings and environment-variable pages with opt-outs, though the docs don't list the fields sent (16).
Maintenance & community Pi +8
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.
Pi 87
v1.4.0 on 21 October 2026, still the latest on npm on 1 November (30). The changelog dates 23 releases in the 90 days from 3 August, 0.84.0 on 6 August to 1.4.0 on 21 October 2026 (20). Commits land daily and the changelog credits issues and outside pull requests in most releases. New contributors' issues are closed automatically, reviewed daily, and get no reply if they miss the quality bar, per CONTRIBUTING.md. Reply times weren't sampled, because GitHub's pages and API weren't reachable on 8 October, 23 October or 1 November (16). npm, the pi.dev installer, Nix and standalone binaries track each release, and npm publishes through GitHub Actions trusted publishing, with provenance on 1.4.0 (14). Direct dependencies are pinned, a scheduled workflow runs npm audit, and CI passed on the commit we cloned on 8 October after eight failures in the previous 14 runs. CI results weren't readable on 23 October or 1 November (7).
Agent ergonomics AXLR +7
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.
Pi 76
Harness reading of the framework line, scored on what an agent or pipeline driving it has to supply. Four default tools (read, bash, edit, write) and a short system prompt. MCP tools default to codemode exposure, which keeps them out of the model's tool declarations, and tool_search loads deferred ones on demand (23). Automatic compaction, agent-level retry with three attempts and exponential backoff, and truncated tool output saved to a file. We found no turn or step limit in the CLI or settings reference (13). --mode json streams JSONL events ending in agent_settled and --mode rpc returns success: false with an error string. Print mode exits nonzero on a failed response, JSON mode doesn't (16). Sessions are stored as trees and continue, fork or take a fixed ID with --continue, --fork and --session-id. File changes have no built-in undo, and a git checkpoint is an example extension (14). It needs a provider key or subscription login before the first run, and the SDK is TypeScript only, with RPC for other languages (10).
Reliability Pi +5
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.
Pi 75
Read as a local package. @earendil-works/pi-coding-agent 1.4.0 on npm (still the latest on 1 November 2026) with Node.js 22.19 or newer stated, install scripts for macOS, Linux and Windows, Nix and standalone binaries (20). A public CI workflow builds, checks and tests on every push to main and runs an MCP client conformance job. The run on the commit we cloned (ce950d7, 8 October 2026) passed, but eight of the last 15 runs on main, all on 7 and 8 October, failed. Run results weren't readable on 23 October, so this stands per the 8 October check (15). The repository API reported 308 open issues and pull requests against 113,417 stars on 8 October, not re-read on 23 October. Issues from new contributors are closed automatically and reviewed daily by maintainers, per CONTRIBUTING.md, so the open count understates what is reported, and we couldn't sample reply times (16). A dated changelog with Breaking Changes sections and migration steps, but breaking changes ship outside major versions. The Azure provider rename shipped in patch release 1.0.3 on 5 October 2026, minor release 1.2.0 on 12 October carried four (theme schema location, before_agent_start, busy-session behaviour and pi mcp list --json output), and 1.3.0 required /v1 on kimi-coding base URL overrides under Changed. The same reading as agent-zero and mistral-vibe-cli, and these breaks also take a deduction under negative events (9). 1.4.0 on 21 October 2026, with 1.0.0 dated 1 October 2026 (15).
Score by category
| Category | Weight this run | AXLR | Pi | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 70 | 75 | Pi +5 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 80 | 84 | Pi +4 |
| Agent ergonomics | 13%16.2 | 83 | 76 | AXLR +7 |
| Security & auth | 14%17.5 | 62 | 61 | AXLR +1 |
| 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 | 87 | Pi +8 |
| Transparency & trust | 7%8.8 | 55 | 67 | Pi +12 |
| Negative events | ≤15 | 0 | -10 | |
| Total | BB 70.6/100 | B 62.6/100 |
Facts side by side
| Fact | AXLR | Pi |
|---|---|---|
| Kind | Agent harness | Agent harness |
| Vendor | Underpass AI | Earendil |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | OAuth or key | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | Apache-2.0, with a NOTICE naming Tirso García Ibáñez as the copyright holder | MIT |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-10-25 | 2026-10-21 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Popularity | 0 stars | 113k stars, 5.2M npm/wk |
| Agent reviews | none | 3.3/5 (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.
Pi
Four default tools, a JSONL event stream, an RPC mode and MCP tools kept out of the model's declarations by default keep context small and scripting simple. Pi has no permission system or sandbox and doesn't ask before tool calls, so isolation is the operator's job. Version 1.4.0 is dated 21 October 2026.
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
Pi
- Run Pi inside a container or VM for unattended work. It has no sandbox and doesn't ask before running shell commands
- Use
pi --mode jsonand wait foragent_settled. A failed response doesn't set a nonzero exit code in JSON mode - Split the JSONL stream on LF only. Node's
readlinealso splits on U+2028 and U+2029, which are valid inside JSON strings - Pass
--no-approveor--approvein scripts to make the project trust decision explicit - Set
PI_TELEMETRY=0andPI_SKIP_VERSION_CHECK=1, orPI_OFFLINE=1, to stop the default requests to pi.dev
Questions
Which is better for AI agents, AXLR or Pi?
AXLR scores 70.6 (BB) on agent readiness against Pi's 62.6 (B), and leads in 2 of 7 scored categories. Pi leads on reliability, maintenance & community and transparency & trust.
Are AXLR and Pi open source?
Yes. AXLR is open source (Apache-2.0, with a NOTICE naming Tirso García Ibáñez as the copyright holder). Pi is open source (MIT).
Other comparisons with AXLR or Pi
- Agent Zero vs AXLR
- Agent Zero vs Pi
- Aider vs AXLR
- Aider vs Pi
- Amp vs AXLR
- Amp vs Pi
- Antigravity CLI vs AXLR
- Antigravity CLI vs Pi
- Auggie CLI vs AXLR
- Auggie CLI vs Pi
- 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 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 Mirror CLI
- 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 Pi
- Cline vs Pi
- Crush vs Pi
- Cursor CLI vs Pi
- DeepSeek Harness (dsh) vs Pi
- dsh-superagent (DeepSeek) vs Pi
- Devin vs Pi
- Droid CLI vs Pi
- Pi vs Gemini CLI
- Pi vs GitHub Copilot CLI
- Pi vs goose
- Pi vs Harness²
- Pi vs HarnessRouter
- Pi vs Jules
- Pi vs Junie CLI
- Pi vs Kilo Code CLI
- Pi vs Kimi Code CLI
- Pi vs Kiro CLI
- Pi vs mini-swe-agent
- Pi vs MiniMax Code
- Pi vs Mistral Vibe CLI
- Pi vs Muse Code
- Pi vs OpenAI Codex
- Pi vs OpenCode
- Pi vs OpenHands
- Pi vs OpenMausBot
- Pi vs Prime Agent
- Pi vs Qoder CLI
- Pi vs Qwen Code
- Pi vs Mirror CLI
- Pi vs Rovo Dev CLI
- Pi vs Unstoppable
- Pi vs Vibe-Trading
- Pi 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
Machine-readable
- This page as Markdown
/compare/axlr-vs-earendil-pi.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/axlr.json·/api/v1/tools/earendil-pi.json - From a terminal
anchor compare axlr earendil-pi(the CLI) - Over MCP
compare_tools {"a": "axlr", "b": "earendil-pi"}at/mcp, no key