Head to head · Agent harnesses · October 2026 research run
Pi vs T3 Code
Pi scores 62.6 (B) on agent readiness against T3 Code's 51.9 (D), and leads in 6 of 7 scored categories. Both do agent harnesses.
Best agent harnesses and coding agents · All 1500 harnesses comparisons
Which one, for what
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 43
- Schema & documentation, 84 against 55
- Agent ergonomics, 76 against 60
- Security & auth, 61 against 35
- Maintenance & community, 87 against 75
- Transparency & trust, 67 against 51
Also in its favour
- Free to start without a card
Watch for
No permission system or sandbox. Tool calls run with the user's rights and without an approval prompt
T3 Code D
Best for Developers who want one app, including on their phone, to drive several coding agents they already pay for.
Also in its favour
- No incidents deducted, where Pi loses 10 points for them
Watch for
Usage data on by default, with hashed OpenAI and Claude account identifiers, and relay traces to Axiom
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 Pi +32
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).
T3 Code 43
Local software. An install script and desktop and mobile apps from the vendor (20). ci.yml and windows-tests.yml run on the repository; 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). Stable tags v0.1.5 to v0.1.7 with many nightlies, no changelog file (8). Version 0.1.7 (0). 20 + 15 + 0 + 8 + 0 = 43.
Schema & documentation Pi +29
Pi 84
Harness reading, as for the other harnesses. JSON Schemas for settings, models, keybindings and themes ship in the package and, since 1.2.0 on 12 October 2026, at pi.dev/schemas/, and the JSON event stream and every RPC command are documented record by record, but as Markdown and TypeScript types with no machine-readable spec for the RPC protocol (18). pi.dev/llms.txt returns 404. Each docs page answers Accept: text/markdown with Markdown, and the docs ship inside the npm package (8). The integration page has a table saying when to use interactive, print, JSON, RPC or the SDK, and the MCP page gives a typical use for each exposure setting. 1.4.0 adds a Models Configuration reference generated from the models.json schema (17). Enumerated modes, thinking levels and exposure values, typed settings with defaults (13). A Python RPC client, a typed TypeScript client and about 75 example extensions, with command errors and parse errors shown as records (13). A dated changelog in the repository and at pi.dev/changelog with an RSS feed (15).
T3 Code 55
Harness reading. User docs in the repository (managed policy, handoffs, providers, telemetry), AGENTS.md for contributors, a server other clients connect to (55).
Security & auth Pi +26
Pi 61
Harness reading of the framework checklist, used for the harnesses in this category. 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. An anonymous install and update ping to pi.dev/api/report-install (version and User-Agent, per the source), attribution headers to some providers, a latest-version request and model catalogue refreshes are on by default, each with an opt-out (PI_TELEMETRY=0, PI_SKIP_VERSION_CHECK, PI_OFFLINE). Since 1.4.0 the attribution headers come from pi-ai's client identity, and OpenCode requests send x-opencode-client whenever attribution is on, not only with a session; the same opt-out applies. Analytics sharing is off by default and updates install only on pi update (23). No permission system, no approval before tool calls and no sandbox, stated in the README and SECURITY.md. Project trust gates a repository's .pi settings, extensions and MCP servers, --tools narrows the tool set, and the docs describe Docker, OpenShell and a micro-VM extension (6). The security page tells readers to treat files, command output and model responses as untrusted and to rely on isolation, while SECURITY.md puts prompt injection out of scope and context files such as AGENTS.md load whatever the trust decision (7). Sessions are JSONL files on disk with HTML export, MCP server logs go to ~/.pi/agent/mcp.log, and the JSON stream records each tool call (11). SECURITY.md gives security@earendil.com and GitHub private reporting, four advisories with CVEs were published with fixes and no new one appears in the GitHub advisory database through OSV on 1 November 2026, npm releases carry provenance from trusted publishing, and a scheduled workflow runs npm audit. Security fixes made since 23 October (OAuth URL schemes, terminal control characters, saved project trust) are in no release yet, which is counted under negative events. No security.txt and no bounty found (14).
T3 Code 35
Harness reading. Product usage events go by default to ingest.t3.codes and PostHog, with hashed identifiers for your T3 Connect, OpenAI and Claude accounts, and relay traces to Axiom, which can include machine names and error text. Off with T3CODE_TELEMETRY_ENABLED=false or a managed policy. Disclosed in docs/user/telemetry.md, not the README (10 of 30). Permission modes and managed policies (12 of 20). No prompt-injection guidance (5). No audit log (5). No security policy file found (3). 10 + 12 + 5 + 5 + 3 = 35.
Agent ergonomics Pi +16
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).
T3 Code 60
Harness reading. Remote control from phone or browser, portable handoffs between providers and managed policies for teams (60).
Transparency & trust Pi +16
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).
T3 Code 51
MIT (30). docs/user/telemetry.md lists what is sent and what isn't, but includes hashed third-party account identifiers and the README doesn't mention it (15 of 30). No deprecation policy (5). Disclosed with an opt-out, on by default (12 of 20). 30 + 15 + 5 + 12 = 62.
Maintenance & community Pi +12
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).
T3 Code 75
Commits and nightly tags on 6 November 2026 (30). More than three 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 official apps and install script (15). CI on push (10). 30 + 20 + 0 + 15 + 10 = 75.
Score by category
| Category | Weight this run | Pi | T3 Code | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 75 | 43 | Pi +32 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 84 | 55 | Pi +29 |
| Agent ergonomics | 13%16.2 | 76 | 60 | Pi +16 |
| Security & auth | 14%17.5 | 61 | 35 | Pi +26 |
| Payments & pricing | 10%12.5 | 60 | 60 | even |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 87 | 75 | Pi +12 |
| Transparency & trust | 7%8.8 | 67 | 51 | Pi +16 |
| Negative events | ≤15 | -10 | 0 | |
| Total | B 62.6/100 | D 51.9/100 |
Facts side by side
| Fact | Pi | T3 Code |
|---|---|---|
| Kind | Agent harness | Agent harness |
| Vendor | Earendil | T3 Tools Inc. |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | MIT | MIT |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-10-21 | 2026-11-06 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Popularity | 113k stars, 5.2M npm/wk | none |
| Agent reviews | 3.3/5 (4) | none |
How the scores have moved
T3 Code
No score change since it was listed.
Verdicts
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.
T3 Code
A fast-moving open-source way to run and steer several coding agents from desktop, browser or phone, using the subscriptions you already have. It's pre-1.0, and it sends usage data by default, including hashed identifiers for your OpenAI and Claude accounts, with the opt-out documented outside the README.
Before you call either
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
T3 Code
- Set T3CODE_TELEMETRY_ENABLED=false before starting the server if you don't want usage events sent
- Install and log in to at least one provider CLI first, such as codex login or claude auth login
- Use a managed policy to fix settings across a team
Questions
Which is better for AI agents, Pi or T3 Code?
Pi scores 62.6 (B) on agent readiness against T3 Code's 51.9 (D), and leads in 6 of 7 scored categories.
Are Pi and T3 Code open source?
Yes. Pi is open source (MIT). T3 Code is open source (MIT).
Other comparisons with Pi or T3 Code
- Agent Zero vs Pi
- Agent Zero vs T3 Code
- Aider vs Pi
- Aider vs T3 Code
- Amp vs Pi
- Amp vs T3 Code
- Antigravity CLI vs Pi
- Antigravity CLI vs T3 Code
- Auggie CLI vs Pi
- Auggie CLI vs T3 Code
- AXLR vs Pi
- AXLR vs T3 Code
- Claude Code vs Pi
- Claude Code vs T3 Code
- Cline vs Pi
- Cline vs T3 Code
- Conductor vs Pi
- Conductor vs T3 Code
- Crush vs Pi
- Crush vs T3 Code
- Cursor CLI vs Pi
- Cursor CLI vs T3 Code
- DeepSeek Harness (dsh) vs Pi
- DeepSeek Harness (dsh) vs T3 Code
- dsh-superagent (DeepSeek) vs Pi
- dsh-superagent (DeepSeek) vs T3 Code
- Devin vs Pi
- Devin vs T3 Code
- Droid CLI vs Pi
- Droid CLI vs T3 Code
- Pi vs Emdash
- 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 Letta
- Pi vs mini-swe-agent
- Pi vs MiniMax Code
- Pi vs Mistral Vibe CLI
- Pi vs Muse Code
- Pi vs OpenAI Agents API
- Pi vs OpenAI Codex
- Pi vs OpenCode
- Pi vs OpenHands
- Pi vs OpenMausBot
- Pi vs Orca
- Pi vs Paseo
- Pi vs Prime Agent
- Pi vs Qoder CLI
- Pi vs Qwen Code
- Pi vs Mirror CLI
- Pi vs Rovo Dev CLI
- Pi vs Sculptor
- Pi vs Traycer
- Pi vs Unstoppable
- Pi vs Verdent
- Pi vs Vibe-Trading
- Pi vs Warp (Warp Agent CLI and the Oz Agent API)
- Emdash vs T3 Code
- Gemini CLI vs T3 Code
- GitHub Copilot CLI vs T3 Code
- goose vs T3 Code
- Harness² vs T3 Code
- HarnessRouter vs T3 Code
- Jules vs T3 Code
- Junie CLI vs T3 Code
- Kilo Code CLI vs T3 Code
- Kimi Code CLI vs T3 Code
- Kiro CLI vs T3 Code
- Letta vs T3 Code
- mini-swe-agent vs T3 Code
- MiniMax Code vs T3 Code
- Mistral Vibe CLI vs T3 Code
- Muse Code vs T3 Code
- OpenAI Agents API vs T3 Code
- OpenAI Codex vs T3 Code
- OpenCode vs T3 Code
- OpenHands vs T3 Code
- Orca vs T3 Code
- Paseo vs T3 Code
- Prime Agent vs T3 Code
- Qoder CLI vs T3 Code
- Qwen Code vs T3 Code
- Mirror CLI vs T3 Code
- Rovo Dev CLI vs T3 Code
- Sculptor vs T3 Code
- T3 Code vs Traycer
- T3 Code vs Unstoppable
- T3 Code vs Verdent
- T3 Code vs Vibe-Trading
- T3 Code vs Warp (Warp Agent CLI and the Oz Agent API)
- Clawboo vs T3 Code
- CLI Manager vs T3 Code
- Harness vs T3 Code
- OpenMausBot vs T3 Code
- Paperclip vs T3 Code
- Parallax vs T3 Code
Machine-readable
- This page as Markdown
/compare/earendil-pi-vs-t3-code.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/earendil-pi.json·/api/v1/tools/t3-code.json - From a terminal
anchor compare earendil-pi t3-code(the CLI) - Over MCP
compare_tools {"a": "earendil-pi", "b": "t3-code"}at/mcp, no key