{ "data": { "a": { "slug": "earendil-pi", "name": "Pi", "vendor": "Earendil", "vendorUrl": "https://pi.dev", "kind": "harness", "category": "agent-harnesses", "summary": "Pi is an open-source terminal coding agent from Earendil, run on the owner's machine with any of 15 or more model providers. It has interactive, print, JSON and RPC modes, a TypeScript SDK and a built-in MCP client.", "url": "https://www.anchorterminal.com/tools/earendil-pi", "markdownUrl": "https://www.anchorterminal.com/tools/earendil-pi.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/earendil-pi.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/earendil-pi.json", "dns": "earendil-pi.grade.anchorterminal.com", "repo": "https://github.com/earendil-works/pi", "license": "MIT", "transports": [], "packages": [ { "registry": "npm", "name": "@earendil-works/pi-coding-agent" } ], "auth": "none", "authNotes": "No Pi account needed. Model providers are connected with `/login` (a subscription or an API key, stored in `~/.pi/agent/auth.json`) or with environment variables such as `ANTHROPIC_API_KEY`. MCP servers take headers, bearer tokens from the environment or OAuth, with tokens kept in `~/.pi/agent/mcp-auth.json`. Radius, the optional hosted gateway, needs its own sign-in or `RADIUS_API_KEY`.", "pricing": "free", "pricingNotes": "Free and MIT, with no paid edition of the harness. The owner pays the model provider. Radius, Earendil's optional hosted gateway, is an early alpha sold by prepaid credits, and no public price list was found (checked 2026-10-23).", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the repository or the docs (checked 2026-10-23).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 113417, "npmWeekly": 5201697, "pypiWeekly": null, "asOf": "2026-10-08" }, "docsUrl": "https://pi.dev/docs/latest", "capabilities": [ "agent.harness", "agent.mcp-client" ], "tags": [ "open-source", "local", "free", "no-card", "typescript", "mcp", "json-output", "rpc", "no-sandbox" ], "lastRelease": "2026-10-21", "graded": true, "anchor": { "graded": true, "score": 62.6, "grade": "B", "agentReady": false, "rank": 550, "ranked": true, "rankOf": 1510, "categoryRank": 13, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 76, "maintenance": 87, "payments": 60, "reliability": 75, "schema": 84, "security": 61, "transparency": 67 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-01" }, "negative": -10, "negativeNotes": [ "2026-06-08. GHSA-jfgx-wxx8-mp94 (CVE-2026-54328, high). Temporary extension installs used predictable paths under the system temp directory, so another local user on a shared Linux host could plant extension code that Pi then loaded. Fixed in 0.78.1. Fixed, published and four months old, -2. https://github.com/earendil-works/pi/security/advisories/GHSA-jfgx-wxx8-mp94", "2026-06-08. GHSA-mqxh-6gq7-558m (CVE-2026-54325, medium). Before 0.79.0 Pi loaded a repository's `.pi` settings and extensions without asking, so starting it in a cloned repository could run that repository's code. Fixed in 0.79.0 with project trust. Fixed and published, -2. https://github.com/earendil-works/pi/security/advisories/GHSA-mqxh-6gq7-558m", "2026-06-08. GHSA-7v5m-pr3q-6453 (CVE-2026-54326, low, XSS in HTML session exports) and GHSA-r95r-rj6r-c39x (CVE-2026-54327, low, a race in `auth.json` permissions). Both fixed in 0.78.1. Recorded without a deduction. https://github.com/earendil-works/pi/security/advisories", "2026-10-12. Minor release 1.2.0 listed four breaking changes under Breaking Changes (the theme schema location, `before_agent_start` firing for custom-message runs, the busy-session behaviour and `pi mcp list --json` output), after patch release 1.0.3 on 5 October renamed the Azure provider, with no advance notice found for either. The changelog follows semantic versioning and these are 1.x releases. One term for breaking changes in minor and patch releases without notice, -3, as microsoft-agent-framework and agno took. https://github.com/earendil-works/pi/blob/main/packages/coding-agent/CHANGELOG.md", "2026-10-23 to 2026-10-29. Security fixes to Pi's own code are on main and in no release on 1 November 2026, the latest being 1.4.0 of 21 October. The unreleased changelog says MCP sign-in now rejects OAuth metadata URLs that aren't http or https (\"Before, a malicious MCP server could supply a `file:` or custom protocol URL\", commit 9ffd27c, 23 October), that the login dialog no longer opens non-web URLs or prints control characters (89c921d, 26 October), and that a saved \"Do not trust\" decision is no longer ignored (31ade0e, 29 October). No advisory was found. -3, as growthbook's unreleased fixes took. https://github.com/earendil-works/pi/blob/main/packages/coding-agent/CHANGELOG.md" ], "verdict": "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.", "bestFor": "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.", "strengths": [ "Four default tools (read, bash, edit, write), with MCP tools reachable through codemode scripts and not declared to the model by default", "`--mode json` streams JSONL events and `--mode rpc` takes JSONL commands, both documented record by record, with a Python client example", "Built-in MCP client for stdio and streamable HTTP servers with OAuth, per-tool exposure settings and a conformance job in CI", "Project trust stops a repository's `.pi` settings, extensions and MCP servers loading until approved, and non-interactive modes skip them by default", "npm releases carry SLSA provenance from GitHub Actions trusted publishing, and the installer pins transitive dependencies" ], "weaknesses": [ "No permission system or sandbox. Tool calls run with the user's rights and without an approval prompt", "An anonymous install and update ping to pi.dev and a latest-version request are on by default", "Four advisories published in June 2026, one rated high and one medium, all fixed by 0.79.0. Fixes made since 23 October were unreleased on 1 November", "No privacy policy for pi.dev or the CLI found, and pi.dev has no security.txt", "Eight of the last 15 CI runs on main failed on 7 and 8 October 2026, and breaking changes ship in patch and minor releases (1.0.3, 1.2.0)" ], "agentNotes": [ "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 json` and wait for `agent_settled`. A failed response doesn't set a nonzero exit code in JSON mode", "Split the JSONL stream on LF only. Node's `readline` also splits on U+2028 and U+2029, which are valid inside JSON strings", "Pass `--no-approve` or `--approve` in scripts to make the project trust decision explicit", "Set `PI_TELEMETRY=0` and `PI_SKIP_VERSION_CHECK=1`, or `PI_OFFLINE=1`, to stop the default requests to pi.dev" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 3.3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 62.6 } ], "editorialScores": { "ergonomics": 76, "maintenance": 87, "payments": 60, "reliability": 75, "schema": 84, "security": 61, "transparency": 64 }, "provenanceScore": 69, "checked": { "categories": { "ergonomics": "2026-11-01", "maintenance": "2026-11-01", "payments": "2026-11-01", "reliability": "2026-11-01", "schema": "2026-11-01", "security": "2026-11-01", "transparency": "2026-11-01" }, "last": "2026-11-01", "lastMoved": "2026-11-01", "oldest": "2026-11-01", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "curl -fsSL https://pi.dev/install.sh | sh # or: npm install -g --ignore-scripts @earendil-works/pi-coding-agent", "headless": { "command": "pi --mode json --no-session --no-approve \"$TASK\"", "env": { "PI_SKIP_VERSION_CHECK": "1", "PI_TELEMETRY": "0" } } }, "letme": { "capability": "https://letme.dev/agent.harness", "tool": "https://letme.dev/earendil-pi" }, "area": "frameworks", "provenance": { "legalEntity": "Earendil Inc.", "domain": "pi.dev", "domainRegistered": "2024-01-30", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://pi.dev/changelog", "securityTxt": "none", "checked": "2026-11-01", "notes": [ "The pi.dev, earendil.com and radius.earendil.com footers read Earendil Inc. The Radius alpha terms of 1 September 2026 name Earendil Works Co., and the README calls the company Earendil Works.", "We found no terms or privacy page for pi.dev or the CLI. pi.dev/terms, pi.dev/privacy, earendil.com/privacy and radius.earendil.com/privacy return 404 (23 October 2026; pi.dev/terms and pi.dev/privacy again on 1 November 2026). Terms exist only for Radius, at radius.earendil.com/terms.", "pi.dev/.well-known/security.txt returns 404 (23 October and 1 November 2026) and earendil.com/.well-known/security.txt returned 404 (23 October 2026). SECURITY.md gives security@earendil.com and GitHub private reporting.", "RDAP for pi.dev gives a registration date of 2024-01-30 with Cloudflare as registrar. The README says the domain was donated by exe.dev.", "The repository moved from badlogic/pi-mono to earendil-works/pi, and the npm package from @mariozechner/pi-coding-agent to @earendil-works/pi-coding-agent at 0.74.0, per the advisories." ], "score": 69 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/earendil-pi.json", "live": { "slug": "earendil-pi", "versions": [ { "registry": "github", "name": "earendil-works/pi", "version": "v1.5.0", "released": "2026-11-02", "seenAt": "2026-11-06T23:23:11.66948223Z" }, { "registry": "npm", "name": "@earendil-works/pi-coding-agent", "version": "1.5.0", "seenAt": "2026-11-06T23:23:11.446666701Z" } ], "githubStars": 120503, "npmWeekly": 6067871, "securityTxt": { "url": "https://pi.dev/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T15:59:52.683123313Z" }, "domain": { "domain": "pi.dev", "registered": "2024-01-30", "source": "https://pubapi.registry.google/rdap/domain/pi.dev", "checkedAt": "2026-11-01T14:24:30.063651336Z" }, "pages": [ { "url": "https://pi.dev/changelog", "kind": "deprecations", "status": 200, "checkedAt": "2026-11-07T14:16:26.732700883Z", "changedAt": "2026-11-03T07:55:44.918705875Z", "fingerprint": "8f309eae070e" } ], "github": { "repo": "earendil-works/pi", "checkedAt": "2026-11-02T08:45:40.305774501Z", "stars": 119451, "archived": false, "issuesEnabled": true, "pushedAt": "2026-11-02T08:38:33Z", "openIssues": 243, "openPRs": 73, "issuesOpened90d": 2943, "issuesClosed90d": 2773, "prsMerged90d": 349, "ci": { "branch": "main", "runs": 50, "success": 36, "failure": 5, "other": 9, "latest": "success", "latestAt": "2026-11-01T23:16:53Z" }, "advisories": [ { "ghsa": "GHSA-mqxh-6gq7-558m", "cve": "CVE-2026-54325", "severity": "medium", "published": "2026-06-08T15:54:14Z" }, { "ghsa": "GHSA-jfgx-wxx8-mp94", "cve": "CVE-2026-54328", "severity": "high", "published": "2026-06-08T15:54:13Z" }, { "ghsa": "GHSA-r95r-rj6r-c39x", "cve": "CVE-2026-54327", "severity": "low", "published": "2026-06-08T15:54:12Z" }, { "ghsa": "GHSA-7v5m-pr3q-6453", "cve": "CVE-2026-54326", "severity": "low", "published": "2026-06-08T15:54:11Z" } ] }, "updatedAt": "2026-11-07T15:59:52.683123313Z" } }, "answer": "Pi scores 62.6 (B) on agent readiness against Emdash's 53.9 (D), and leads in 6 of 7 scored categories.", "b": { "slug": "emdash", "name": "Emdash", "vendor": "General Action, Inc.", "vendorUrl": "https://emdash.sh", "kind": "harness", "category": "agent-harnesses", "summary": "Emdash is an open-source desktop app that runs coding agents such as Claude Code, Codex, OpenCode and Amp in parallel, each in its own Git worktree, locally or on remote machines over SSH, with issue intake and pull requests.", "url": "https://www.anchorterminal.com/tools/emdash", "markdownUrl": "https://www.anchorterminal.com/tools/emdash.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/emdash.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/emdash.json", "dns": "emdash.grade.anchorterminal.com", "repo": "https://github.com/generalaction/emdash", "license": "Apache-2.0", "transports": [], "packages": [], "auth": "none", "pricing": "free", "pricingNotes": "Free and open source. You pay for the coding agents it runs, through your own subscriptions or API keys (checked 2026-11-07).", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No payment protocol in the repository or README (checked 2026-11-07).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-07" }, "docsUrl": "https://emdash.sh/docs", "capabilities": [ "agent.harness", "agent.multi-agent" ], "tags": [ "open-source", "apache-2.0", "desktop-app", "telemetry", "new" ], "lastRelease": "2026-11-06", "graded": true, "anchor": { "graded": true, "score": 53.9, "grade": "D", "agentReady": false, "rank": 933, "ranked": true, "rankOf": 1510, "categoryRank": 35, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 55, "maintenance": 70, "payments": 60, "reliability": 55, "schema": 55, "security": 38, "transparency": 54 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-11-07" }, "negative": 0, "verdict": "A mature open-source app for parallel coding agents in Git worktrees, with issue intake from a dozen trackers and remote machines over SSH. Telemetry is on unless you turn it off, and no test workflow was found in the repository.", "bestFor": "Developers who want parallel agents in worktrees, fed from their issue tracker, locally or over SSH.", "strengths": [ "Each task in its own Git worktree and branch", "Issues from Linear, GitHub, Jira, GitLab, Asana and more go straight to an agent", "Works on remote machines over SSH", "Apache 2.0, version 1.2, with macOS, Windows and Linux builds" ], "weaknesses": [ "Telemetry on unless turned off in Settings or with TELEMETRY_ENABLED=false", "No test workflow found, only consistency and release workflows", "No security policy file" ], "agentNotes": [ "Launch with TELEMETRY_ENABLED=false if you don't want telemetry", "Use the SSH mode to keep agents on a remote machine" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "D", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 53.9 } ], "editorialScores": { "ergonomics": 55, "maintenance": 70, "payments": 60, "reliability": 55, "schema": 55, "security": 38, "transparency": 68 }, "provenanceScore": 40, "checked": { "categories": { "ergonomics": "2026-11-07", "maintenance": "2026-11-07", "payments": "2026-11-07", "reliability": "2026-11-07", "schema": "2026-11-07", "security": "2026-11-07", "transparency": "2026-11-07" }, "last": "2026-11-07", "oldest": "2026-11-07", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "brew install --cask emdash" }, "letme": { "capability": "https://letme.dev/agent.harness", "tool": "https://letme.dev/emdash" }, "area": "frameworks", "provenance": { "legalEntity": "General Action, Inc.", "domain": "emdash.sh", "domainRegistered": "", "domainNote": "Not looked up: RDAP isn't requested under the 1 November 2026 rules.", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-11-07", "notes": [ "The licence names General Action, Inc.. The repository is github.com/generalaction/emdash." ], "score": 40 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/emdash.json", "live": { "slug": "emdash", "securityTxt": { "url": "https://emdash.sh/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:01:15.230445185Z" }, "updatedAt": "2026-11-07T16:01:15.230445185Z" } }, "edges": [ { "by": 29, "category": "schema", "leads": "earendil-pi", "name": "Schema \u0026 documentation", "reasons": { "a": "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).", "b": "Harness reading. Docs site and a workspace server package (55)." }, "scores": { "a": 84, "b": 55 } }, { "by": 23, "category": "security", "leads": "earendil-pi", "name": "Security \u0026 auth", "reasons": { "a": "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).", "b": "Harness reading. Telemetry is described as optional and disabled in Settings or with TELEMETRY_ENABLED=false, which reads as on by default (15 of 30). Worktree per task and remote machines over SSH (10 of 20). No prompt-injection guidance (5). No audit log (5). No security policy file found (3). 15 + 10 + 5 + 5 + 3 = 38." }, "scores": { "a": 61, "b": 38 } }, { "by": 21, "category": "ergonomics", "leads": "earendil-pi", "name": "Agent ergonomics", "reasons": { "a": "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).", "b": "Harness reading. Issue intake from Linear, GitHub, Jira and others, diff review, pull requests and CI checks in one place, local or over SSH (55)." }, "scores": { "a": 76, "b": 55 } }, { "by": 20, "category": "reliability", "leads": "earendil-pi", "name": "Reliability", "reasons": { "a": "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).", "b": "Local software. Homebrew cask and installers for macOS, Windows and Linux (20). A code-consistency check and release workflows; no test workflow found (10). GitHub issues and pull requests weren't read (GitHub's pages refuse these sessions), so that line is scored absent (0). Stable tags to v1.2.11, release notes on GitHub (10). Version 1.2.11 (15). 20 + 10 + 0 + 10 + 15 = 55." }, "scores": { "a": 75, "b": 55 } }, { "by": 17, "category": "maintenance", "leads": "earendil-pi", "name": "Maintenance \u0026 community", "reasons": { "a": "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).", "b": "v1.2.11 on 6 November 2026 (30). v1.2.9, v1.2.10 and v1.2.11 within two weeks (20). GitHub issues and pull requests weren't read (GitHub's pages refuse these sessions), so that line is scored absent (0). Current installers and Homebrew cask (15). Release workflows, no test CI (5). 30 + 20 + 0 + 15 + 5 = 70." }, "scores": { "a": 87, "b": 70 } }, { "by": 13, "category": "transparency", "leads": "earendil-pi", "name": "Transparency \u0026 trust", "reasons": { "a": "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).", "b": "Apache 2.0 (30). A telemetry page on the docs site (not read) (18 of 30). No deprecation policy (5). Disclosed with an opt-out (15 of 20). 30 + 18 + 5 + 15 = 68." }, "scores": { "a": 67, "b": 54 } } ], "facts": [ { "a": "Agent harness", "b": "Agent harness", "name": "Kind" }, { "a": "Earendil", "b": "General Action, Inc.", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "", "b": "", "name": "Transports" }, { "a": "None", "b": "None", "name": "Auth" }, { "a": "Free", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "MIT", "b": "Apache-2.0", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "no", "name": "llms.txt" }, { "a": "2026-10-21", "b": "2026-11-06", "name": "Last release" }, { "a": "no document linked", "b": "no document linked", "name": "Terms last updated" }, { "a": "no document linked", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "113k stars, 5.2M npm/wk", "b": "none", "name": "Popularity" }, { "a": "3.3/5 (4)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "Pi scores 62.6 (B) on agent readiness against Emdash's 53.9 (D), and leads in 6 of 7 scored categories.", "question": "Which is better for AI agents, Pi or Emdash?" }, { "answer": "Yes. Pi is open source (MIT). Emdash is open source (Apache-2.0).", "question": "Are Pi and Emdash open source?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 75 against 55", "Schema \u0026 documentation, 84 against 55", "Agent ergonomics, 76 against 55", "Security \u0026 auth, 61 against 38", "Maintenance \u0026 community, 87 against 70", "Transparency \u0026 trust, 67 against 54" ], "also": [ "Free to start without a card" ], "goodFor": "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.", "slug": "earendil-pi", "watchFor": "No permission system or sandbox. Tool calls run with the user's rights and without an approval prompt" }, { "aheadOn": null, "also": [ "No incidents deducted, where Pi loses 10 points for them" ], "goodFor": "Developers who want parallel agents in worktrees, fed from their issue tracker, locally or over SSH.", "slug": "emdash", "watchFor": "Telemetry on unless turned off in Settings or with TELEMETRY_ENABLED=false" } ], "history": { "earendil-pi": [ { "causes": [ "event" ], "date": "2026-11-01", "delta": -6, "from": 68.6, "fromGrade": "B", "to": 62.6, "toGrade": "B" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.2, "from": 68.4, "fromGrade": "B", "to": 68.6, "toGrade": "B" } ], "emdash": null }, "job": { "capability": "agent.harness", "name": "Agent harnesses" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agent-zero-vs-earendil-pi.json", "title": "Agent Zero vs Pi", "url": "https://www.anchorterminal.com/compare/agent-zero-vs-earendil-pi" }, { "json": "https://www.anchorterminal.com/compare/agent-zero-vs-emdash.json", "title": "Agent Zero vs Emdash", "url": "https://www.anchorterminal.com/compare/agent-zero-vs-emdash" }, { "json": "https://www.anchorterminal.com/compare/aider-vs-earendil-pi.json", "title": "Aider vs Pi", "url": "https://www.anchorterminal.com/compare/aider-vs-earendil-pi" }, { "json": "https://www.anchorterminal.com/compare/aider-vs-emdash.json", "title": "Aider vs Emdash", "url": "https://www.anchorterminal.com/compare/aider-vs-emdash" }, { "json": "https://www.anchorterminal.com/compare/amp-vs-earendil-pi.json", "title": "Amp vs Pi", "url": "https://www.anchorterminal.com/compare/amp-vs-earendil-pi" }, { "json": "https://www.anchorterminal.com/compare/amp-vs-emdash.json", "title": "Amp vs Emdash", "url": "https://www.anchorterminal.com/compare/amp-vs-emdash" }, { "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-earendil-pi.json", "title": "Antigravity CLI vs Pi", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-earendil-pi" }, { "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-emdash.json", "title": "Antigravity CLI vs Emdash", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-emdash" }, { "json": "https://www.anchorterminal.com/compare/auggie-vs-earendil-pi.json", "title": "Auggie CLI vs Pi", "url": "https://www.anchorterminal.com/compare/auggie-vs-earendil-pi" }, { "json": "https://www.anchorterminal.com/compare/auggie-vs-emdash.json", "title": "Auggie CLI vs Emdash", "url": "https://www.anchorterminal.com/compare/auggie-vs-emdash" }, { "json": "https://www.anchorterminal.com/compare/axlr-vs-earendil-pi.json", "title": "AXLR vs Pi", "url": "https://www.anchorterminal.com/compare/axlr-vs-earendil-pi" }, { "json": "https://www.anchorterminal.com/compare/axlr-vs-emdash.json", "title": "AXLR vs Emdash", "url": "https://www.anchorterminal.com/compare/axlr-vs-emdash" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-earendil-pi.json", "title": "Claude Code vs Pi", "url": "https://www.anchorterminal.com/compare/claude-code-vs-earendil-pi" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-emdash.json", "title": "Claude Code vs Emdash", "url": "https://www.anchorterminal.com/compare/claude-code-vs-emdash" }, { "json": "https://www.anchorterminal.com/compare/cline-vs-earendil-pi.json", "title": "Cline vs Pi", "url": "https://www.anchorterminal.com/compare/cline-vs-earendil-pi" }, { "json": "https://www.anchorterminal.com/compare/cline-vs-emdash.json", "title": "Cline vs Emdash", "url": "https://www.anchorterminal.com/compare/cline-vs-emdash" }, { "json": "https://www.anchorterminal.com/compare/conductor-vs-earendil-pi.json", "title": "Conductor vs Pi", "url": "https://www.anchorterminal.com/compare/conductor-vs-earendil-pi" }, { "json": "https://www.anchorterminal.com/compare/conductor-vs-emdash.json", "title": "Conductor vs Emdash", "url": "https://www.anchorterminal.com/compare/conductor-vs-emdash" }, { "json": "https://www.anchorterminal.com/compare/crush-vs-earendil-pi.json", "title": "Crush vs Pi", "url": "https://www.anchorterminal.com/compare/crush-vs-earendil-pi" }, { "json": "https://www.anchorterminal.com/compare/crush-vs-emdash.json", "title": "Crush vs Emdash", "url": "https://www.anchorterminal.com/compare/crush-vs-emdash" }, { "json": "https://www.anchorterminal.com/compare/cursor-cli-vs-earendil-pi.json", "title": "Cursor CLI vs Pi", "url": "https://www.anchorterminal.com/compare/cursor-cli-vs-earendil-pi" }, { "json": "https://www.anchorterminal.com/compare/cursor-cli-vs-emdash.json", "title": "Cursor CLI vs Emdash", "url": "https://www.anchorterminal.com/compare/cursor-cli-vs-emdash" }, { "json": "https://www.anchorterminal.com/compare/deepseek-harness-vs-earendil-pi.json", "title": "DeepSeek Harness (dsh) vs Pi", "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-earendil-pi" }, { "json": "https://www.anchorterminal.com/compare/deepseek-harness-vs-emdash.json", "title": "DeepSeek Harness (dsh) vs Emdash", "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-emdash" }, { "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-earendil-pi.json", "title": "dsh-superagent (DeepSeek) vs Pi", "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-earendil-pi" }, { "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-emdash.json", "title": "dsh-superagent (DeepSeek) vs Emdash", "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-emdash" }, { "json": "https://www.anchorterminal.com/compare/devin-vs-earendil-pi.json", "title": "Devin vs Pi", "url": "https://www.anchorterminal.com/compare/devin-vs-earendil-pi" }, { "json": "https://www.anchorterminal.com/compare/devin-vs-emdash.json", "title": "Devin vs Emdash", "url": "https://www.anchorterminal.com/compare/devin-vs-emdash" }, { "json": "https://www.anchorterminal.com/compare/droid-cli-vs-earendil-pi.json", "title": "Droid CLI vs Pi", "url": "https://www.anchorterminal.com/compare/droid-cli-vs-earendil-pi" }, { "json": "https://www.anchorterminal.com/compare/droid-cli-vs-emdash.json", "title": "Droid CLI vs Emdash", "url": "https://www.anchorterminal.com/compare/droid-cli-vs-emdash" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-gemini-cli.json", "title": "Pi vs Gemini CLI", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-gemini-cli" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-github-copilot-cli.json", "title": "Pi vs GitHub Copilot CLI", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-github-copilot-cli" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-goose.json", "title": "Pi vs goose", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-goose" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-harness2.json", "title": "Pi vs Harness²", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-harnessrouter.json", "title": "Pi vs HarnessRouter", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-harnessrouter" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-jules.json", "title": "Pi vs Jules", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-jules" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-junie.json", "title": "Pi vs Junie CLI", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-junie" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-kilo-code-cli.json", "title": "Pi vs Kilo Code CLI", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-kilo-code-cli" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-kimi-code-cli.json", "title": "Pi vs Kimi Code CLI", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-kimi-code-cli" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-kiro-cli.json", "title": "Pi vs Kiro CLI", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-kiro-cli" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-letta.json", "title": "Pi vs Letta", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-letta" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-mini-swe-agent.json", "title": "Pi vs mini-swe-agent", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-mini-swe-agent" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-minimax-code.json", "title": "Pi vs MiniMax Code", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-minimax-code" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-mistral-vibe-cli.json", "title": "Pi vs Mistral Vibe CLI", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-mistral-vibe-cli" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-muse-code.json", "title": "Pi vs Muse Code", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-muse-code" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-openai-agents-api.json", "title": "Pi vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-openai-codex.json", "title": "Pi vs OpenAI Codex", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-openai-codex" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-opencode.json", "title": "Pi vs OpenCode", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-opencode" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-openhands.json", "title": "Pi vs OpenHands", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-openhands" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-openmausbot.json", "title": "Pi vs OpenMausBot", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-openmausbot" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-orca.json", "title": "Pi vs Orca", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-orca" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-paseo.json", "title": "Pi vs Paseo", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-paseo" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-prime-agent.json", "title": "Pi vs Prime Agent", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-prime-agent" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-qoder-cli.json", "title": "Pi vs Qoder CLI", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-qoder-cli" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-qwen-code.json", "title": "Pi vs Qwen Code", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-qwen-code" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-reflection-mirror.json", "title": "Pi vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-reflection-mirror" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-rovo-dev-cli.json", "title": "Pi vs Rovo Dev CLI", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-rovo-dev-cli" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-sculptor.json", "title": "Pi vs Sculptor", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-sculptor" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-t3-code.json", "title": "Pi vs T3 Code", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-t3-code" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-traycer.json", "title": "Pi vs Traycer", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-traycer" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-unstoppable.json", "title": "Pi vs Unstoppable", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-unstoppable" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-verdent.json", "title": "Pi vs Verdent", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-vibe-trading.json", "title": "Pi vs Vibe-Trading", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-vibe-trading" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-warp.json", "title": "Pi vs Warp (Warp Agent CLI and the Oz Agent API)", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-warp" }, { "json": "https://www.anchorterminal.com/compare/emdash-vs-gemini-cli.json", "title": "Emdash vs Gemini CLI", "url": "https://www.anchorterminal.com/compare/emdash-vs-gemini-cli" }, { "json": "https://www.anchorterminal.com/compare/emdash-vs-github-copilot-cli.json", "title": "Emdash vs GitHub Copilot CLI", "url": "https://www.anchorterminal.com/compare/emdash-vs-github-copilot-cli" }, { "json": "https://www.anchorterminal.com/compare/emdash-vs-goose.json", "title": "Emdash vs goose", "url": "https://www.anchorterminal.com/compare/emdash-vs-goose" }, { "json": "https://www.anchorterminal.com/compare/emdash-vs-harness2.json", "title": "Emdash vs Harness²", "url": "https://www.anchorterminal.com/compare/emdash-vs-harness2" }, { "json": "https://www.anchorterminal.com/compare/emdash-vs-harnessrouter.json", "title": "Emdash vs HarnessRouter", "url": "https://www.anchorterminal.com/compare/emdash-vs-harnessrouter" }, { "json": "https://www.anchorterminal.com/compare/emdash-vs-jules.json", "title": "Emdash vs Jules", "url": "https://www.anchorterminal.com/compare/emdash-vs-jules" }, { "json": "https://www.anchorterminal.com/compare/emdash-vs-junie.json", "title": "Emdash vs Junie CLI", "url": "https://www.anchorterminal.com/compare/emdash-vs-junie" }, { "json": "https://www.anchorterminal.com/compare/emdash-vs-kilo-code-cli.json", "title": "Emdash vs Kilo Code CLI", "url": "https://www.anchorterminal.com/compare/emdash-vs-kilo-code-cli" }, { "json": "https://www.anchorterminal.com/compare/emdash-vs-kimi-code-cli.json", "title": "Emdash vs Kimi Code CLI", "url": "https://www.anchorterminal.com/compare/emdash-vs-kimi-code-cli" }, { "json": "https://www.anchorterminal.com/compare/emdash-vs-kiro-cli.json", "title": "Emdash vs Kiro CLI", "url": "https://www.anchorterminal.com/compare/emdash-vs-kiro-cli" }, { "json": "https://www.anchorterminal.com/compare/emdash-vs-letta.json", "title": "Emdash vs Letta", "url": "https://www.anchorterminal.com/compare/emdash-vs-letta" }, { "json": "https://www.anchorterminal.com/compare/emdash-vs-mini-swe-agent.json", "title": "Emdash vs mini-swe-agent", "url": "https://www.anchorterminal.com/compare/emdash-vs-mini-swe-agent" }, { "json": "https://www.anchorterminal.com/compare/emdash-vs-minimax-code.json", "title": "Emdash vs MiniMax Code", "url": "https://www.anchorterminal.com/compare/emdash-vs-minimax-code" }, { "json": "https://www.anchorterminal.com/compare/emdash-vs-mistral-vibe-cli.json", "title": "Emdash vs Mistral Vibe CLI", "url": "https://www.anchorterminal.com/compare/emdash-vs-mistral-vibe-cli" }, { "json": "https://www.anchorterminal.com/compare/emdash-vs-muse-code.json", "title": "Emdash vs Muse Code", "url": "https://www.anchorterminal.com/compare/emdash-vs-muse-code" }, { "json": "https://www.anchorterminal.com/compare/emdash-vs-openai-agents-api.json", "title": "Emdash vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/emdash-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/emdash-vs-openai-codex.json", "title": "Emdash vs OpenAI Codex", "url": "https://www.anchorterminal.com/compare/emdash-vs-openai-codex" }, { "json": "https://www.anchorterminal.com/compare/emdash-vs-opencode.json", "title": "Emdash vs OpenCode", "url": "https://www.anchorterminal.com/compare/emdash-vs-opencode" }, { "json": "https://www.anchorterminal.com/compare/emdash-vs-openhands.json", "title": "Emdash vs OpenHands", "url": "https://www.anchorterminal.com/compare/emdash-vs-openhands" }, { "json": "https://www.anchorterminal.com/compare/emdash-vs-openmausbot.json", "title": "Emdash vs OpenMausBot", "url": "https://www.anchorterminal.com/compare/emdash-vs-openmausbot" }, { "json": "https://www.anchorterminal.com/compare/emdash-vs-orca.json", "title": "Emdash vs Orca", "url": "https://www.anchorterminal.com/compare/emdash-vs-orca" }, { "json": "https://www.anchorterminal.com/compare/emdash-vs-paseo.json", "title": "Emdash vs Paseo", "url": "https://www.anchorterminal.com/compare/emdash-vs-paseo" }, { "json": "https://www.anchorterminal.com/compare/emdash-vs-prime-agent.json", "title": "Emdash vs Prime Agent", "url": "https://www.anchorterminal.com/compare/emdash-vs-prime-agent" }, { "json": "https://www.anchorterminal.com/compare/emdash-vs-qoder-cli.json", "title": "Emdash vs Qoder CLI", "url": "https://www.anchorterminal.com/compare/emdash-vs-qoder-cli" }, { "json": "https://www.anchorterminal.com/compare/emdash-vs-qwen-code.json", "title": "Emdash vs Qwen Code", "url": "https://www.anchorterminal.com/compare/emdash-vs-qwen-code" }, { "json": "https://www.anchorterminal.com/compare/emdash-vs-reflection-mirror.json", "title": "Emdash vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/emdash-vs-reflection-mirror" }, { "json": "https://www.anchorterminal.com/compare/emdash-vs-rovo-dev-cli.json", "title": "Emdash vs Rovo Dev CLI", "url": "https://www.anchorterminal.com/compare/emdash-vs-rovo-dev-cli" }, { "json": "https://www.anchorterminal.com/compare/emdash-vs-sculptor.json", "title": "Emdash vs Sculptor", "url": "https://www.anchorterminal.com/compare/emdash-vs-sculptor" }, { "json": "https://www.anchorterminal.com/compare/emdash-vs-t3-code.json", "title": "Emdash vs T3 Code", "url": "https://www.anchorterminal.com/compare/emdash-vs-t3-code" }, { "json": "https://www.anchorterminal.com/compare/emdash-vs-traycer.json", "title": "Emdash vs Traycer", "url": "https://www.anchorterminal.com/compare/emdash-vs-traycer" }, { "json": "https://www.anchorterminal.com/compare/emdash-vs-unstoppable.json", "title": "Emdash vs Unstoppable", "url": "https://www.anchorterminal.com/compare/emdash-vs-unstoppable" }, { "json": "https://www.anchorterminal.com/compare/emdash-vs-verdent.json", "title": "Emdash vs Verdent", "url": "https://www.anchorterminal.com/compare/emdash-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/emdash-vs-vibe-trading.json", "title": "Emdash vs Vibe-Trading", "url": "https://www.anchorterminal.com/compare/emdash-vs-vibe-trading" }, { "json": "https://www.anchorterminal.com/compare/emdash-vs-warp.json", "title": "Emdash vs Warp (Warp Agent CLI and the Oz Agent API)", "url": "https://www.anchorterminal.com/compare/emdash-vs-warp" }, { "json": "https://www.anchorterminal.com/compare/clawboo-vs-emdash.json", "title": "Clawboo vs Emdash", "url": "https://www.anchorterminal.com/compare/clawboo-vs-emdash" }, { "json": "https://www.anchorterminal.com/compare/cli-manager-vs-emdash.json", "title": "CLI Manager vs Emdash", "url": "https://www.anchorterminal.com/compare/cli-manager-vs-emdash" }, { "json": "https://www.anchorterminal.com/compare/emdash-vs-harness-autonomous.json", "title": "Emdash vs Harness", "url": "https://www.anchorterminal.com/compare/emdash-vs-harness-autonomous" }, { "json": "https://www.anchorterminal.com/compare/emdash-vs-paperclip.json", "title": "Emdash vs Paperclip", "url": "https://www.anchorterminal.com/compare/emdash-vs-paperclip" }, { "json": "https://www.anchorterminal.com/compare/emdash-vs-parallax-agents.json", "title": "Emdash vs Parallax", "url": "https://www.anchorterminal.com/compare/emdash-vs-parallax-agents" } ], "panel": null, "scores": [ { "by": 20, "earendil-pi": 75, "edge": "earendil-pi", "emdash": 55, "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 29, "earendil-pi": 84, "edge": "earendil-pi", "emdash": 55, "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 21, "earendil-pi": 76, "edge": "earendil-pi", "emdash": 55, "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "by": 23, "earendil-pi": 61, "edge": "earendil-pi", "emdash": 38, "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "by": 0, "earendil-pi": 60, "edge": "", "emdash": 60, "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 17, "earendil-pi": 87, "edge": "earendil-pi", "emdash": 70, "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 13, "earendil-pi": 67, "edge": "earendil-pi", "emdash": 54, "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Pi scores 62.6 (B) on agent readiness against Emdash's 53.9 (D), and leads in 6 of 7 scored categories. Both do agent harnesses.", "tasks": null, "tutorials": [], "verdicts": { "earendil-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.", "emdash": "A mature open-source app for parallel coding agents in Git worktrees, with issue intake from a dozen trackers and remote machines over SSH. Telemetry is on unless you turn it off, and no test workflow was found in the repository." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/earendil-pi-vs-emdash", "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-emdash.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/earendil-pi-vs-emdash.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/earendil-pi-vs-emdash.min.md" }, "markdown": "Pi scores 62.6 (B) on agent readiness against Emdash's 53.9 (D), and leads in 6 of 7 scored categories. Both do agent harnesses.\n\n- Pi: grade B, 62.6/100, rank #550 of 1510. Markdown https://www.anchorterminal.com/tools/earendil-pi.md · JSON https://www.anchorterminal.com/api/v1/tools/earendil-pi.json\n- Emdash: grade D, 53.9/100, rank #933 of 1510. Markdown https://www.anchorterminal.com/tools/emdash.md · JSON https://www.anchorterminal.com/api/v1/tools/emdash.json\n- Best agent harnesses and coding agents: https://www.anchorterminal.com/best/agent-harnesses/index.md\n- All 1500 harnesses comparisons: https://www.anchorterminal.com/compare/agent-harnesses/index.md\n\n## Which one, for what\n\n### Pi (B)\n\nGood 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.\n\nAhead on:\n- Reliability, 75 against 55\n- Schema \u0026 documentation, 84 against 55\n- Agent ergonomics, 76 against 55\n- Security \u0026 auth, 61 against 38\n- Maintenance \u0026 community, 87 against 70\n- Transparency \u0026 trust, 67 against 54\n\nAlso in its favour:\n- Free to start without a card\n\nWatch for: No permission system or sandbox. Tool calls run with the user's rights and without an approval prompt\n\n### Emdash (D)\n\nGood for: Developers who want parallel agents in worktrees, fed from their issue tracker, locally or over SSH.\n\nAlso in its favour:\n- No incidents deducted, where Pi loses 10 points for them\n\nWatch for: Telemetry on unless turned off in Settings or with TELEMETRY_ENABLED=false\n\n\n## Why the edge\n\n### Schema \u0026 documentation: Pi +29\n\n- 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).\n- Emdash (55): Harness reading. Docs site and a workspace server package (55).\n\n### Security \u0026 auth: Pi +23\n\n- 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).\n- Emdash (38): Harness reading. Telemetry is described as optional and disabled in Settings or with TELEMETRY_ENABLED=false, which reads as on by default (15 of 30). Worktree per task and remote machines over SSH (10 of 20). No prompt-injection guidance (5). No audit log (5). No security policy file found (3). 15 + 10 + 5 + 5 + 3 = 38.\n\n### Agent ergonomics: Pi +21\n\n- 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).\n- Emdash (55): Harness reading. Issue intake from Linear, GitHub, Jira and others, diff review, pull requests and CI checks in one place, local or over SSH (55).\n\n### Reliability: Pi +20\n\n- 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).\n- Emdash (55): Local software. Homebrew cask and installers for macOS, Windows and Linux (20). A code-consistency check and release workflows; no test workflow found (10). GitHub issues and pull requests weren't read (GitHub's pages refuse these sessions), so that line is scored absent (0). Stable tags to v1.2.11, release notes on GitHub (10). Version 1.2.11 (15). 20 + 10 + 0 + 10 + 15 = 55.\n\n### Maintenance \u0026 community: Pi +17\n\n- 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).\n- Emdash (70): v1.2.11 on 6 November 2026 (30). v1.2.9, v1.2.10 and v1.2.11 within two weeks (20). GitHub issues and pull requests weren't read (GitHub's pages refuse these sessions), so that line is scored absent (0). Current installers and Homebrew cask (15). Release workflows, no test CI (5). 30 + 20 + 0 + 15 + 5 = 70.\n\n### Transparency \u0026 trust: Pi +13\n\n- 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).\n- Emdash (54): Apache 2.0 (30). A telemetry page on the docs site (not read) (18 of 30). No deprecation policy (5). Disclosed with an opt-out (15 of 20). 30 + 18 + 5 + 15 = 68.\n\n## Score by category\n\n| Category | Weight | Pi | Emdash | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 75 | 55 | Pi +20 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 84 | 55 | Pi +29 |\n| Agent ergonomics | 13% (16.2 this run) | 76 | 55 | Pi +21 |\n| Security \u0026 auth | 14% (17.5 this run) | 61 | 38 | Pi +23 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 60 | 60 | even |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 87 | 70 | Pi +17 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 67 | 54 | Pi +13 |\n| Negative events | ≤15 | -10 | 0 | |\n| **Total** | | **62.6 · B** | **53.9 · D** | |\n\n## Facts side by side\n\n| Fact | Pi | Emdash |\n| --- | --- | --- |\n| Kind | Agent harness | Agent harness |\n| Vendor | Earendil | General Action, Inc. |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | | |\n| Auth | None | None |\n| Pricing | Free | Free |\n| x402 | no | no |\n| Licence | MIT | Apache-2.0 |\n| Read-only variant documented | no | no |\n| llms.txt | no | no |\n| Last release | 2026-10-21 | 2026-11-06 |\n| Terms last updated | no document linked | no document linked |\n| Privacy policy last updated | no document linked | no document linked |\n| Popularity | 113k stars, 5.2M npm/wk | none |\n| Agent reviews | 3.3/5 (4) | none |\n\n## How the scores have moved\n\n### Pi\n\n- -6.0 on 1 November 2026: negative event\n- +0.2 on 27 October 2026: checklist\n\n### Emdash\n\nNo score change since it was listed.\n\n## Verdicts\n\n**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.\n\n**Emdash.** A mature open-source app for parallel coding agents in Git worktrees, with issue intake from a dozen trackers and remote machines over SSH. Telemetry is on unless you turn it off, and no test workflow was found in the repository.\n\n## Before you call either\n\n### Pi\n\n1. Run Pi inside a container or VM for unattended work. It has no sandbox and doesn't ask before running shell commands\n2. Use `pi --mode json` and wait for `agent_settled`. A failed response doesn't set a nonzero exit code in JSON mode\n3. Split the JSONL stream on LF only. Node's `readline` also splits on U+2028 and U+2029, which are valid inside JSON strings\n4. Pass `--no-approve` or `--approve` in scripts to make the project trust decision explicit\n5. Set `PI_TELEMETRY=0` and `PI_SKIP_VERSION_CHECK=1`, or `PI_OFFLINE=1`, to stop the default requests to pi.dev\n\n### Emdash\n\n1. Launch with TELEMETRY_ENABLED=false if you don't want telemetry\n2. Use the SSH mode to keep agents on a remote machine\n\n## Questions\n\n### Which is better for AI agents, Pi or Emdash?\n\nPi scores 62.6 (B) on agent readiness against Emdash's 53.9 (D), and leads in 6 of 7 scored categories.\n\n### Are Pi and Emdash open source?\n\nYes. Pi is open source (MIT). Emdash is open source (Apache-2.0).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/earendil-pi-vs-emdash.json, and with the fewest tokens: https://www.anchorterminal.com/compare/earendil-pi-vs-emdash.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"earendil-pi\", \"b\": \"emdash\"}`. From a terminal: `anchor compare earendil-pi emdash`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/earendil-pi.json and https://www.anchorterminal.com/api/v1/tools/emdash.json\n\n## Other comparisons with Pi or Emdash\n\n- [Agent Zero vs Pi](https://www.anchorterminal.com/compare/agent-zero-vs-earendil-pi.md)\n- [Agent Zero vs Emdash](https://www.anchorterminal.com/compare/agent-zero-vs-emdash.md)\n- [Aider vs Pi](https://www.anchorterminal.com/compare/aider-vs-earendil-pi.md)\n- [Aider vs Emdash](https://www.anchorterminal.com/compare/aider-vs-emdash.md)\n- [Amp vs Pi](https://www.anchorterminal.com/compare/amp-vs-earendil-pi.md)\n- [Amp vs Emdash](https://www.anchorterminal.com/compare/amp-vs-emdash.md)\n- [Antigravity CLI vs Pi](https://www.anchorterminal.com/compare/antigravity-cli-vs-earendil-pi.md)\n- [Antigravity CLI vs Emdash](https://www.anchorterminal.com/compare/antigravity-cli-vs-emdash.md)\n- [Auggie CLI vs Pi](https://www.anchorterminal.com/compare/auggie-vs-earendil-pi.md)\n- [Auggie CLI vs Emdash](https://www.anchorterminal.com/compare/auggie-vs-emdash.md)\n- [AXLR vs Pi](https://www.anchorterminal.com/compare/axlr-vs-earendil-pi.md)\n- [AXLR vs Emdash](https://www.anchorterminal.com/compare/axlr-vs-emdash.md)\n- [Claude Code vs Pi](https://www.anchorterminal.com/compare/claude-code-vs-earendil-pi.md)\n- [Claude Code vs Emdash](https://www.anchorterminal.com/compare/claude-code-vs-emdash.md)\n- [Cline vs Pi](https://www.anchorterminal.com/compare/cline-vs-earendil-pi.md)\n- [Cline vs Emdash](https://www.anchorterminal.com/compare/cline-vs-emdash.md)\n- [Conductor vs Pi](https://www.anchorterminal.com/compare/conductor-vs-earendil-pi.md)\n- [Conductor vs Emdash](https://www.anchorterminal.com/compare/conductor-vs-emdash.md)\n- [Crush vs Pi](https://www.anchorterminal.com/compare/crush-vs-earendil-pi.md)\n- [Crush vs Emdash](https://www.anchorterminal.com/compare/crush-vs-emdash.md)\n- [Cursor CLI vs Pi](https://www.anchorterminal.com/compare/cursor-cli-vs-earendil-pi.md)\n- [Cursor CLI vs Emdash](https://www.anchorterminal.com/compare/cursor-cli-vs-emdash.md)\n- [DeepSeek Harness (dsh) vs Pi](https://www.anchorterminal.com/compare/deepseek-harness-vs-earendil-pi.md)\n- [DeepSeek Harness (dsh) vs Emdash](https://www.anchorterminal.com/compare/deepseek-harness-vs-emdash.md)\n- [dsh-superagent (DeepSeek) vs Pi](https://www.anchorterminal.com/compare/deepseek-superagent-vs-earendil-pi.md)\n- [dsh-superagent (DeepSeek) vs Emdash](https://www.anchorterminal.com/compare/deepseek-superagent-vs-emdash.md)\n- [Devin vs Pi](https://www.anchorterminal.com/compare/devin-vs-earendil-pi.md)\n- [Devin vs Emdash](https://www.anchorterminal.com/compare/devin-vs-emdash.md)\n- [Droid CLI vs Pi](https://www.anchorterminal.com/compare/droid-cli-vs-earendil-pi.md)\n- [Droid CLI vs Emdash](https://www.anchorterminal.com/compare/droid-cli-vs-emdash.md)\n- [Pi vs Gemini CLI](https://www.anchorterminal.com/compare/earendil-pi-vs-gemini-cli.md)\n- [Pi vs GitHub Copilot CLI](https://www.anchorterminal.com/compare/earendil-pi-vs-github-copilot-cli.md)\n- [Pi vs goose](https://www.anchorterminal.com/compare/earendil-pi-vs-goose.md)\n- [Pi vs Harness²](https://www.anchorterminal.com/compare/earendil-pi-vs-harness2.md)\n- [Pi vs HarnessRouter](https://www.anchorterminal.com/compare/earendil-pi-vs-harnessrouter.md)\n- [Pi vs Jules](https://www.anchorterminal.com/compare/earendil-pi-vs-jules.md)\n- [Pi vs Junie CLI](https://www.anchorterminal.com/compare/earendil-pi-vs-junie.md)\n- [Pi vs Kilo Code CLI](https://www.anchorterminal.com/compare/earendil-pi-vs-kilo-code-cli.md)\n- [Pi vs Kimi Code CLI](https://www.anchorterminal.com/compare/earendil-pi-vs-kimi-code-cli.md)\n- [Pi vs Kiro CLI](https://www.anchorterminal.com/compare/earendil-pi-vs-kiro-cli.md)\n- [Pi vs Letta](https://www.anchorterminal.com/compare/earendil-pi-vs-letta.md)\n- [Pi vs mini-swe-agent](https://www.anchorterminal.com/compare/earendil-pi-vs-mini-swe-agent.md)\n- [Pi vs MiniMax Code](https://www.anchorterminal.com/compare/earendil-pi-vs-minimax-code.md)\n- [Pi vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/earendil-pi-vs-mistral-vibe-cli.md)\n- [Pi vs Muse Code](https://www.anchorterminal.com/compare/earendil-pi-vs-muse-code.md)\n- [Pi vs OpenAI Agents API](https://www.anchorterminal.com/compare/earendil-pi-vs-openai-agents-api.md)\n- [Pi vs OpenAI Codex](https://www.anchorterminal.com/compare/earendil-pi-vs-openai-codex.md)\n- [Pi vs OpenCode](https://www.anchorterminal.com/compare/earendil-pi-vs-opencode.md)\n- [Pi vs OpenHands](https://www.anchorterminal.com/compare/earendil-pi-vs-openhands.md)\n- [Pi vs OpenMausBot](https://www.anchorterminal.com/compare/earendil-pi-vs-openmausbot.md)\n- [Pi vs Orca](https://www.anchorterminal.com/compare/earendil-pi-vs-orca.md)\n- [Pi vs Paseo](https://www.anchorterminal.com/compare/earendil-pi-vs-paseo.md)\n- [Pi vs Prime Agent](https://www.anchorterminal.com/compare/earendil-pi-vs-prime-agent.md)\n- [Pi vs Qoder CLI](https://www.anchorterminal.com/compare/earendil-pi-vs-qoder-cli.md)\n- [Pi vs Qwen Code](https://www.anchorterminal.com/compare/earendil-pi-vs-qwen-code.md)\n- [Pi vs Mirror CLI](https://www.anchorterminal.com/compare/earendil-pi-vs-reflection-mirror.md)\n- [Pi vs Rovo Dev CLI](https://www.anchorterminal.com/compare/earendil-pi-vs-rovo-dev-cli.md)\n- [Pi vs Sculptor](https://www.anchorterminal.com/compare/earendil-pi-vs-sculptor.md)\n- [Pi vs T3 Code](https://www.anchorterminal.com/compare/earendil-pi-vs-t3-code.md)\n- [Pi vs Traycer](https://www.anchorterminal.com/compare/earendil-pi-vs-traycer.md)\n- [Pi vs Unstoppable](https://www.anchorterminal.com/compare/earendil-pi-vs-unstoppable.md)\n- [Pi vs Verdent](https://www.anchorterminal.com/compare/earendil-pi-vs-verdent.md)\n- [Pi vs Vibe-Trading](https://www.anchorterminal.com/compare/earendil-pi-vs-vibe-trading.md)\n- [Pi vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/earendil-pi-vs-warp.md)\n- [Emdash vs Gemini CLI](https://www.anchorterminal.com/compare/emdash-vs-gemini-cli.md)\n- [Emdash vs GitHub Copilot CLI](https://www.anchorterminal.com/compare/emdash-vs-github-copilot-cli.md)\n- [Emdash vs goose](https://www.anchorterminal.com/compare/emdash-vs-goose.md)\n- [Emdash vs Harness²](https://www.anchorterminal.com/compare/emdash-vs-harness2.md)\n- [Emdash vs HarnessRouter](https://www.anchorterminal.com/compare/emdash-vs-harnessrouter.md)\n- [Emdash vs Jules](https://www.anchorterminal.com/compare/emdash-vs-jules.md)\n- [Emdash vs Junie CLI](https://www.anchorterminal.com/compare/emdash-vs-junie.md)\n- [Emdash vs Kilo Code CLI](https://www.anchorterminal.com/compare/emdash-vs-kilo-code-cli.md)\n- [Emdash vs Kimi Code CLI](https://www.anchorterminal.com/compare/emdash-vs-kimi-code-cli.md)\n- [Emdash vs Kiro CLI](https://www.anchorterminal.com/compare/emdash-vs-kiro-cli.md)\n- [Emdash vs Letta](https://www.anchorterminal.com/compare/emdash-vs-letta.md)\n- [Emdash vs mini-swe-agent](https://www.anchorterminal.com/compare/emdash-vs-mini-swe-agent.md)\n- [Emdash vs MiniMax Code](https://www.anchorterminal.com/compare/emdash-vs-minimax-code.md)\n- [Emdash vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/emdash-vs-mistral-vibe-cli.md)\n- [Emdash vs Muse Code](https://www.anchorterminal.com/compare/emdash-vs-muse-code.md)\n- [Emdash vs OpenAI Agents API](https://www.anchorterminal.com/compare/emdash-vs-openai-agents-api.md)\n- [Emdash vs OpenAI Codex](https://www.anchorterminal.com/compare/emdash-vs-openai-codex.md)\n- [Emdash vs OpenCode](https://www.anchorterminal.com/compare/emdash-vs-opencode.md)\n- [Emdash vs OpenHands](https://www.anchorterminal.com/compare/emdash-vs-openhands.md)\n- [Emdash vs OpenMausBot](https://www.anchorterminal.com/compare/emdash-vs-openmausbot.md)\n- [Emdash vs Orca](https://www.anchorterminal.com/compare/emdash-vs-orca.md)\n- [Emdash vs Paseo](https://www.anchorterminal.com/compare/emdash-vs-paseo.md)\n- [Emdash vs Prime Agent](https://www.anchorterminal.com/compare/emdash-vs-prime-agent.md)\n- [Emdash vs Qoder CLI](https://www.anchorterminal.com/compare/emdash-vs-qoder-cli.md)\n- [Emdash vs Qwen Code](https://www.anchorterminal.com/compare/emdash-vs-qwen-code.md)\n- [Emdash vs Mirror CLI](https://www.anchorterminal.com/compare/emdash-vs-reflection-mirror.md)\n- [Emdash vs Rovo Dev CLI](https://www.anchorterminal.com/compare/emdash-vs-rovo-dev-cli.md)\n- [Emdash vs Sculptor](https://www.anchorterminal.com/compare/emdash-vs-sculptor.md)\n- [Emdash vs T3 Code](https://www.anchorterminal.com/compare/emdash-vs-t3-code.md)\n- [Emdash vs Traycer](https://www.anchorterminal.com/compare/emdash-vs-traycer.md)\n- [Emdash vs Unstoppable](https://www.anchorterminal.com/compare/emdash-vs-unstoppable.md)\n- [Emdash vs Verdent](https://www.anchorterminal.com/compare/emdash-vs-verdent.md)\n- [Emdash vs Vibe-Trading](https://www.anchorterminal.com/compare/emdash-vs-vibe-trading.md)\n- [Emdash vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/emdash-vs-warp.md)\n- [Clawboo vs Emdash](https://www.anchorterminal.com/compare/clawboo-vs-emdash.md)\n- [CLI Manager vs Emdash](https://www.anchorterminal.com/compare/cli-manager-vs-emdash.md)\n- [Emdash vs Harness](https://www.anchorterminal.com/compare/emdash-vs-harness-autonomous.md)\n- [Emdash vs Paperclip](https://www.anchorterminal.com/compare/emdash-vs-paperclip.md)\n- [Emdash vs Parallax](https://www.anchorterminal.com/compare/emdash-vs-parallax-agents.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-07", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Pi vs Emdash", "url": "" } ], "description": "Pi scores 62.6 (B) to Emdash's 53.9 (D) for agent harnesses. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Pi B 62.6", "Emdash D 53.9", "scores" ], "h1": "Pi vs Emdash", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/earendil-pi-vs-emdash", "published": "2026-10-01", "section": "tools", "title": "Pi vs Emdash for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-emdash" }, "tokens": { "markdown": 6100, "slim": 2780 }, "version": 1 }