Head to head · Multi-agent orchestration · October 2026 research run
Crush vs herdr
herdr scores 71.1 (BB) on agent readiness against Crush's 53.3 (D), and leads in 6 of 7 scored categories. Crush leads on maintenance & community. Both do multi-agent orchestration.
Best agent harnesses and coding agents · All 1767 harnesses comparisons
Which one, for what
Crush D
Best for Developers who want a Go terminal agent with a wide provider list, local models and Claude Code-compatible hooks.
Ahead on
- Maintenance & community, 82 against 63
Also in its favour
- Free to start without a card
Watch for
crush run approves every permission request automatically, which the README doesn't mention
herdr BB
Best for A developer who runs several coding agents in terminals, locally or over SSH, and wants one agent to start, prompt and wait on others.
Ahead on
- Reliability, 65 against 52
- Schema & documentation, 91 against 65
- Agent ergonomics, 73 against 52
- Security & auth, 49 against 41
- Payments & pricing, 90 against 83
- Transparency & trust, 70 against 59
Also in its favour
- Agent-ready, a grade of BB or better
- No key needed to call it
- Open source
- No incidents deducted, where Crush loses 6 points for them
Watch for
Version 0.9.5, not yet 1.0, and the last tagged release is 14 October 2026
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.
Schema & documentation herdr +26
Crush 65
Harness reading of the framework line. A JSON Schema for the config at https://charm.land/crush.json (also printed by crush schema), --json on the session commands, and an OpenAPI document that crush server generates from its endpoint list and serves at /v1/docs/openapi.json, which isn't published anywhere we could fetch. crush run output has no typed form (20). No llms.txt (charm.land/llms.txt is a not-found page). The docs are Markdown in the repository and the hooks guide says it was written for humans and agents (5). The README and config docs explain when to allow, deny or hook a tool and warn that configs run as code (12). The schema carries enums and defaults, such as the attribution trailer style, while permissions take bare tool names with no command patterns (11). Many examples for providers, MCP, hooks and local models, with no reference for error messages or exit codes (9). Version tags and GitHub releases with generated notes, which we couldn't open, and no changelog file (8).
herdr 91
Read as a CLI and socket API. herdr api schema --json prints a JSON Schema for requests, responses, errors and events, also at docs/next/api/herdr-api.schema.json (25). Markdown for agents, with skills/herdr/SKILL.md and distribution/agent-guide.md. https://herdr.dev/llms.txt indexes the 0.9.5 docs as raw source files for agents (10). The skill says when to use herdr and when not to, and the socket docs say which layer to use for which job, but the schema itself carries few descriptions (15). The schema has 49 enums and agent names are constrained by a pattern, while some inputs are free strings (12). Many CLI and JSON examples, a documented error shape with codes such as not_found, agent_blocked and events_lost (14). Versioned docs per release and a changelog (15). 25 + 10 + 15 + 12 + 14 + 15 = 91.
Agent ergonomics herdr +21
Crush 52
Harness reading, scored on what an agent or pipeline driving crush run has to supply. About 20 built-in tools, any of which permissions deny hides, MCP servers take per-server disabled_tools, and skills can be turned off or kept out of the model's list. No lazy loading of MCP tools found (17). No turn, time or cost limit on crush run, and the only output controls are --quiet and --verbose (6). Errors come back as plain messages with a non-zero exit, such as the one for an unconfigured provider, with no documented codes and no JSON error record (8). --session and --continue resume a run, and crush session list, show, last, rename and delete take --json (13). One argument starts a run and environment keys are picked up, but there's no SDK, and the HTTP API needs CRUSH_CLIENT_SERVER=1 and is described only in one README section (8).
herdr 73
Framework reading, how much an agent has to carry. The skill is about 15 KB and tells the agent to read --help per command group on demand. Reads take --lines and --source recent (20 of 25). Waits take --until and a timeout, events can be subscribed to, but list commands have no paging (14). Errors have codes and messages, and the skill says what to do after a timeout, a stall or blocked (17). agent prompt --wait submits and waits in one request to avoid a race, agent.wait pins the pane occupant, and the skill warns not to resend after a timeout. No idempotency keys (14). Most commands default to the caller's or focused pane. No SDK, only the CLI and raw socket (8). 20 + 14 + 17 + 14 + 8 = 73.
Maintenance & community Crush +19
Crush 82
v0.99.0 tagged on 29 October 2026 (6 days, 30). 21 release tags from 7 August to 29 October, v0.88.1 to v0.99.0, besides a moving nightly tag that isn't counted (20). The 18 October shields.io counts are struck. The repository's refs show 147 merges into main and 438 commits in the 90 days to 4 November, with 272 open pull requests carrying a merge ref, and new contributors signing the CLA most days. Reply times couldn't be read (12). No SDK, as with other harnesses. npm, Homebrew, Winget, Scoop, apt, yum and NUR builds come from the release workflow (12, held partial). Dependabot, a go mod tidy check in CI and nightly security scans, with CI results unread (8). 30 + 20 + 12 + 12 + 8 = 82.
herdr 63
v0.9.5 on 14 October 2026, 35 days before the check, and the last commit on master on 29 October (20). Six releases from 7 September to 14 October 2026 (20). 495 open issues and 26 open pull requests. The 25 newest issues were labelled triaged with a priority within a day of opening. Unsolicited pull requests are closed automatically and a monthly workflow closes stale issues (15). Not an MCP server and no official SDK (0). Cargo.lock, Dependabot and CI on three systems, run results unread (8). 20 + 20 + 15 + 0 + 8 = 63.
Reliability herdr +13
Crush 52
Local-package reading. @charmland/crush on npm, a Homebrew tap, Winget, Scoop, AUR, Nix, FreeBSD pkg, Charm's apt and yum repositories and release binaries, with supported platforms named in the README (20). The public build workflow runs go test -race -failfast ./... on Linux, macOS and Windows for every push to main and every pull request, but GitHub pages and the API answer 403 to us, so results are unread (15). The 18 October issue and pull request counts came from shields.io badges, a third-party copy of GitHub data, and are struck. The repository's own refs show 2,574 pull requests to #4224, 272 of them open with a merge ref, and 147 merges into main in the 90 days to 4 November. Crash and regression issues couldn't be read (10). Release notes are generated from commit messages, with no CHANGELOG file and no breaking-change headings found. The legacy JSON config is deprecated in favour of crushrc while still loading (7, held partial). v0.99.0, before 1.0, with no stability statement (0). 20 + 15 + 10 + 7 + 0 = 52.
herdr 65
Read as local software, as for agents-tree and Harness. Official release binaries for Linux, macOS and Windows x86_64 with an install script, and Homebrew and mise in the README. The Homebrew formula wasn't read (20). .github/workflows/ci.yml runs checks and tests on ubuntu, macOS and Windows for every push and pull request, but run results couldn't be read from this session, so 15, the value this run gives public CI with unread results. 495 issues were open on 18 November 2026. The 25 newest, opened 15 to 18 November, all carry a triaged label and a priority (p1 or p2), several of them bugs, so reports are sorted within a day but many stay open (15). Semver tags and a Keep a Changelog file with Breaking Changes and Removed sections (15). Version 0.9.5, not 1.0, and not declared stable (0). 20 + 15 + 15 + 15 + 0 = 65.
Transparency & trust herdr +11
Crush 59
FSL-1.1-MIT, source-available, barring competing commercial use and converting each release to MIT on its second anniversary. Code from before 30 May 2025 is MIT. Not an OSI licence today (20). No privacy policy or terms for Crush were found on charm.land, and Hyper's legal pages render by script and weren't read. The README says Hyper is zero-data-retention, while Hyper's own app says some plans aren't and that usage on them may train Hyper's models, so the statements don't agree (8). The JSON config is marked deprecated with no removal date, and no deprecation policy was found (6). The README discloses usage metrics, links the source, says prompts aren't collected and gives two opt-outs, but doesn't mention the alias to the Hyper account (15).
herdr 70
Apache-2.0 (30). herdr.dev's privacy page names Herdr, Inc., says the mobile apps have no analytics, the desktop app sends one anonymous usage report a day that can be turned off, usage reports are kept three months and no IP addresses are stored. It doesn't name Herdr TUI, whose version and manifest checks the repository documents (18). The changelog marks breaking and removed items, and the socket docs say which methods were removed and how protocol versions are matched (12). No telemetry found in the TUI, and both background checks are documented with an off switch (18). 30 + 18 + 12 + 18 = 78.
Security & auth herdr +8
Crush 41
Harness reading of the framework checklist, as for the other harnesses. 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. Usage metrics go to PostHog through data.charm.land by default, keyed to a hashed machine ID, aliased to the Hyper user ID after a Hyper login, and including error messages. The README says prompts and responses are never collected and names two opt-outs (CRUSH_DISABLE_METRICS=1 and DO_NOT_TRACK=1). The provider list is fetched from Catwalk at startup unless turned off, the update check only notifies, and provider keys stay local (15). The TUI asks before bash, edit, write, fetch, download and MCP calls, permissions deny hides tools and PreToolUse hooks can block calls. But crush run approves every permission request in its session automatically (internal/app/app.go in v0.99.0), --yolo skips all prompts, and there's no sandbox, only a refusal list for curl, wget, ssh, sudo, package managers and similar commands (7). No prompt-injection guidance found, and a project's .crushrc and $(...) in crush.json run as code at startup, which the README warns about (3). Logs in ./.crush/logs/crush.log with crush logs, sessions in a local database readable as JSON, and crush stats, with no OpenTelemetry export (9). The organisation's SECURITY.md is a disclosure policy with a reporting address (vt100@charm.sh) and no response time. CI runs CodeQL, Grype and govulncheck nightly and releases are cosign-signed. OSV lists no advisory for the npm package or the Go module. No security.txt and no bug bounty. A disclosure route with no stated time is this run's 7 (was 10). 15 + 7 + 3 + 9 + 7 = 41.
herdr 49
Harness reading of the framework checklist, as for Harness and agents-tree. 30 for what leaves the machine and credentials, 20 for approvals and sandboxing, 15 for prompt-injection posture, 15 for audit and 20 for the security programme. No account, no telemetry found in the source, and a socket file set to 0600. Version and manifest checks reach herdr.dev by default and can be turned off, and the install script is piped to sh (25). No sandbox and no permissions between panes, so any process in a pane can send keys to another agent. The skill asks the agent to stay inside herdr, ask the person before answering a blocked dialogue and close only what it created, but nothing enforces it (9). Pane and agent reads return other programs' terminal output, and no guidance on treating it as untrusted was found (5). A server log, but no per-call audit log found (5). No SECURITY.md or disclosure policy in the repository, and herdr.dev serves no security.txt. CI pins actions to commit SHAs and Dependabot is on (5). 25 + 9 + 5 + 5 + 5 = 49.
Score by category
| Category | Weight | Crush | herdr | Edge |
|---|---|---|---|---|
| Reliability | 16% | 52 | 65 | herdr +13 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13% | 65 | 91 | herdr +26 |
| Agent ergonomics | 13% | 52 | 73 | herdr +21 |
| Security & auth | 14% | 41 | 49 | herdr +8 |
| Payments & pricing | 10% | 83 | 90 | herdr +7 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7% | 82 | 63 | Crush +19 |
| Transparency & trust | 7% | 59 | 70 | herdr +11 |
| Negative events | ≤15 | -6 | 0 | |
| Total | D 53.3/100 | BB 71.1/100 |
Facts side by side
| Fact | Crush | herdr |
|---|---|---|
| Kind | Agent harness | Agent harness |
| Vendor | Charm | herdr |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | OAuth or key | None |
| Pricing | Freemium | Free |
| x402 | no | no |
| Licence | FSL-1.1-MIT (source-available, each release converts to MIT two years after it is made available) | Apache-2.0 |
| Read-only variant documented | no | no |
| llms.txt | no | yes |
| Last release | 2026-10-29 | 2026-10-14 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | 2026-11-02 |
| Popularity | 29k stars, 5.6k npm/wk | 52k stars |
| Agent reviews | 2.3/5 (4) | none |
How the scores have moved
Verdicts
Crush
Works with almost any provider or a local model and needs no Charm account. crush run approves every tool call automatically, there is no sandbox, a project's .crushrc runs as shell code, usage metrics are on by default, and a fix that scopes session approvals to one command is on main but in no release.
herdr
Agents inside a herdr pane can split panes, start other coding agents, prompt them and wait on their state through a CLI and a local socket API with a published JSON Schema. It is pre-1.0 local software with no sandbox, and any process in a pane can type into another agent's terminal.
Before you call either
Crush
- Add
permissions denyrules or a PreToolUse hook beforecrush run. It approves every permission request in its session, and a session approval in v0.99.0 covers later commands in the same directory - Read
.crushrc,crushrcandcrush.jsonin a cloned repository before running Crush there. They execute as shell code at startup - Set
CRUSH_DISABLE_METRICS=1orDO_NOT_TRACK=1to stop usage metrics to data.charm.land - Wrap
crush runin your own timeout. It has no turn, time or cost limit flag - Configure a provider by environment variable or
crushrcfirst. With none,crush runexits with an error asking for interactive setup
herdr
- Check
HERDR_ENV=1before any herdr command. If it isn't set, tell the person you aren't inside herdr and stop - Use
herdr agent prompt <name> --waitrather than a separate prompt and wait, so a fast agent can't finish between the two calls - If a wait times out or stalls, read the pane with
herdr agent readbefore sending the prompt again, since it may have been delivered - If an agent is
blocked, show the person the dialogue and let them answer it - Close only the panes, tabs and workspaces you created, unless the person asks otherwise
Questions
Which is better for AI agents, Crush or herdr?
herdr scores 71.1 (BB) on agent readiness against Crush's 53.3 (D), and leads in 6 of 7 scored categories. Crush leads on maintenance & community.
Are Crush and herdr open source?
No open-source release is listed for Crush. herdr is open source (Apache-2.0).
Other comparisons with Crush or herdr
- Agent Zero vs Crush
- Aider vs Crush
- Amp vs Crush
- Antigravity CLI vs Crush
- Auggie CLI vs Crush
- AXLR vs Crush
- boxes.dev vs Crush
- Claude Code vs Crush
- Click vs Crush
- Cline vs Crush
- Conductor vs Crush
- Crush vs Cursor CLI
- Crush vs DeepSeek Harness (dsh)
- Crush vs dsh-superagent (DeepSeek)
- Crush vs Devin
- Crush vs Droid CLI
- Crush vs Pi
- Crush vs Emdash
- Crush vs Friday
- Crush vs Gemini CLI
- Crush vs GitHub Copilot CLI
- Crush vs goose
- Crush vs Harness²
- Crush vs HarnessRouter
- Crush vs Jules
- Crush vs Junie CLI
- Crush vs Kilo Code CLI
- Crush vs Kimi Code CLI
- Crush vs Kiro CLI
- Crush vs Letta
- Crush vs mini-swe-agent
- Crush vs MiniMax Code
- Crush vs Mistral Vibe CLI
- Crush vs Muse Code
- Crush vs OpenAI Agents API
- Crush vs OpenAI Codex
- Crush vs OpenCode
- Crush vs OpenHands
- Crush vs OpenMausBot
- Crush vs Orca
- Crush vs Paseo
- Crush vs Prime Agent
- Crush vs Qoder CLI
- Crush vs Qwen Code
- Crush vs Mirror CLI
- Crush vs Rovo Dev CLI
- Crush vs Sculptor
- Crush vs T3 Code
- Crush vs Traycer
- Crush vs Unstoppable
- Crush vs Verdent
- Crush vs Vibe-Trading
- Crush vs Warp (Warp Agent CLI and the Oz Agent API)
- Agent Relay vs Crush
- Agent Relay vs herdr
- Amp vs herdr
- Antigravity CLI vs herdr
- Auggie CLI vs herdr
- AXLR vs herdr
- boxes.dev vs herdr
- Claude Code vs herdr
- Clawboo vs Crush
- Clawboo vs herdr
- CLI Manager vs Crush
- CLI Manager vs herdr
- Cline vs herdr
- Conductor vs herdr
- Crush vs Harness
- Crush vs Paperclip
- Crush vs Parallax
- DeepSeek Harness (dsh) vs herdr
- dsh-superagent (DeepSeek) vs herdr
- Devin vs herdr
- Droid CLI vs herdr
- Emdash vs herdr
- Friday vs herdr
- Gemini CLI vs herdr
- GitHub Copilot CLI vs herdr
- goose vs herdr
- Harness vs herdr
- HarnessRouter vs herdr
- herdr vs Jules
- herdr vs Junie CLI
- herdr vs Kilo Code CLI
- herdr vs Kimi Code CLI
- herdr vs Kiro CLI
- herdr vs Letta
- herdr vs MiniMax Code
- herdr vs Mistral Vibe CLI
- herdr vs Muse Code
- herdr vs OpenCode
- herdr vs OpenHands
- herdr vs OpenMausBot
- herdr vs Orca
- herdr vs Paperclip
- herdr vs Parallax
- herdr vs Paseo
- herdr vs Prime Agent
- herdr vs Qoder CLI
- herdr vs Qwen Code
- herdr vs Mirror CLI
- herdr vs Rovo Dev CLI
- herdr vs Sculptor
- herdr vs T3 Code
- herdr vs Traycer
- herdr vs Unstoppable
- herdr vs Verdent
- herdr vs Vibe-Trading
- herdr vs Warp (Warp Agent CLI and the Oz Agent API)
Machine-readable
- This page as Markdown
/compare/crush-vs-herdr.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/crush.json·/api/v1/tools/herdr.json - From a terminal
anchor compare crush herdr(the CLI) - Over MCP
compare_tools {"a": "crush", "b": "herdr"}at/mcp, no key