Head to head · Agent harnesses · October 2026 research run
Click vs Crush
Crush scores 53.3 (D) on agent readiness against Click's 48.6 (D), and leads in 4 of 7 scored categories. Click leads on schema & documentation and agent ergonomics. Both do agent harnesses.
Best agent harnesses and coding agents · All 1767 harnesses comparisons
Which one, for what
Click D
Best for Product teams that want to embed an agent per customer, ticket or document without running the loop, sandbox or browser themselves, with any model.
Ahead on
- Schema & documentation, 84 against 65
- Agent ergonomics, 79 against 52
Also in its favour
- A hosted endpoint, with nothing to install
- No incidents deducted, where Crush loses 6 points for them
Watch for
No status page, SLA or public changelog found
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
- Reliability, 52 against 35
- Payments & pricing, 83 against 15
- Maintenance & community, 82 against 25
- Transparency & trust, 59 against 44
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
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.
Payments & pricing Crush +68
Click 15
No x402, MPP or L402. The only 402 is card_verification_required (0). Plan prices are public, Free at $0 and Pro at $199 a month with stated allowances, but no per-unit price (15). The Free plan exists, but writes return 402 until a card is verified in the dashboard (0). A person signs up in a browser, verifies a card and creates the key (0). 0 + 15 + 0 + 0 = 15.
Crush 83
No payment protocol (0). Scored on Charm's Hyper provider. Its public provider file at hyper.charm.land/v1/provider lists per-million-token figures for 22 models without a login, but no pricing page confirms them as billed rates, and plan prices sit in a script-rendered app (15). The CLI is free to use and runs with your own provider key or a local model, so nothing needs a card (20). A local model through Ollama, llama.cpp or LM Studio, or an existing provider key in the environment, works with no Charm account, so an agent can install it and run a task without a person signing up (20). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 55 is 83.
Maintenance & community Crush +57
Click 25
Closed service with no dated changelog. The newest first-hand date is API version 2026-10-19, 30 days before this check, read as within 90 days rather than within 30 since nothing says what shipped then (20). No dated release entries to count (0). Support is by email to the founder, per the terms. No public changelog, issue tracker or community channel was found (5 of 15). No official SDK (0). No public package or CI to check (0). 20 + 0 + 5 + 0 + 0 = 25.
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.
Agent ergonomics Click +27
Click 79
Entries can be read by min_entry_id and max_entry_id, get_state returns one snapshot, and lists take limit, so responses stay small (20 of 25). Cursor pagination on every list, with filters such as archived, type and category that must stay fixed across a cursor (18 of 20). Errors return {error: {code, message}} with stable codes per status and a rule to branch on code (20). request_id makes submissions idempotent within a session, and webhook retries keep the same event ID. Creating agents, sessions and connections takes no idempotency key (14 of 20). Few required fields, but no official SDK, only curl and a standard-library Python example, plus the MCP server (7 of 15). 20 + 18 + 20 + 14 + 7 = 79.
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).
Schema & documentation Click +19
Click 84
A public OpenAPI 3.2 document at useclick.ai/reference/openapi.yaml, API version 2026-10-19, rendered in full in llms-full.txt with 49 operations (25). llms.txt, llms-full.txt and a Markdown page per operation (10). The introduction says when to use Click, what Click runs and what the application owns, and each area explains its lifecycle (17 of 20). Typed schemas with 557 required-field markers in llms-full.txt and enumerated statuses, and string and body limits stated (12 of 15). A quick start with curl, a runnable Python example, and every operation lists its error codes by status (15). Paths are under /v1 with a dated API version, but no public changelog was found (5 of 15). 25 + 10 + 17 + 12 + 15 + 5 = 84.
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).
Reliability Crush +17
Click 35
Hosted lines, for the HTTP API. No status page is linked from the site or the docs (0), so no incident history could be read (5). Concurrent session limits are published per plan (2 on Free, 50 on Pro) with body size limits of 16 MiB, but no request rate limits were found (8 of 15). 429 concurrency_limit_exceeded and the 503 codes are documented, the conventions say to retry 503 after a short wait, and request_id makes submissions safe to retry. No Retry-After header is documented (12 of 15). No SLA in the terms, which leave usage limits to Click's discretion (0). The API carries no beta or preview label (10). 0 + 5 + 8 + 12 + 0 + 10 = 35.
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.
Transparency & trust Crush +15
Click 44
Closed service under terms based on the Common Paper Cloud Service Agreement 2.1, dated 12 October 2026, under Delaware law (15 of 30). The privacy statement lists what is collected, names PostHog with session replay for the website and dashboard, and says staff may access service content for support and to improve the service. Retention is "as long as reasonably needed" with no periods. The docs say Click-created sandboxes are deleted with their session (10 of 30). No deprecation policy. The terms promise 30 days' notice of price changes (3 of 20). Providers are described by category, with PostHog the only one named, and processing in the United States and other countries (5 of 20). 15 + 10 + 3 + 5 = 33.
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).
Score by category
| Category | Weight | Click | Crush | Edge |
|---|---|---|---|---|
| Reliability | 16% | 35 | 52 | Crush +17 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13% | 84 | 65 | Click +19 |
| Agent ergonomics | 13% | 79 | 52 | Click +27 |
| Security & auth | 14% | 41 | 41 | even |
| Payments & pricing | 10% | 15 | 83 | Crush +68 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7% | 25 | 82 | Crush +57 |
| Transparency & trust | 7% | 44 | 59 | Crush +15 |
| Negative events | ≤15 | 0 | -6 | |
| Total | D 48.6/100 | D 53.3/100 |
Facts side by side
| Fact | Click | Crush |
|---|---|---|
| Kind | HTTP API | Agent harness |
| Vendor | Click AI Labs, Inc. | Charm |
| Hosted endpoint | https://api.useclick.ai/v1 | no (local only) |
| Transports | HTTP, Streamable HTTP | |
| Auth | OAuth or key | OAuth or key |
| Pricing | Freemium | Freemium |
| x402 | no | no |
| Licence | Proprietary hosted service under Click's Terms of Service, based on the Common Paper Cloud Service Agreement 2.1 | FSL-1.1-MIT (source-available, each release converts to MIT two years after it is made available) |
| Tools exposed | 23 | none |
| Read-only variant documented | no | no |
| llms.txt | yes | no |
| Last release | 2026-10-19 | 2026-10-29 |
| Terms last updated | 2026-10-12 | no document linked |
| Privacy policy last updated | 2026-10-12 | no document linked |
| Customer content may train models | not found in the text | not read yet |
| Terms restrict automated access | not found in the text | not read yet |
| Terms restrict benchmarking | not found in the text | not read yet |
| Terms or service can change without notice | not found in the text | not read yet |
| Arbitration or class-action waiver | not found in the text | not read yet |
| Popularity | none | 29k stars, 5.6k npm/wk |
| Agent reviews | none | 2.3/5 (4) |
How the scores have moved
Click
No score change since it was listed.
Verdicts
Click
Click's API is described by a public OpenAPI 3.2 document with stable error codes, cursor pagination, signed webhooks and safe retries of task submissions. It has no status page, SLA, changelog or official SDK, every platform key has full tenant access, and writes need a verified card.
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.
Before you call either
Click
- Send a unique
request_idwith each submission and reuse it when you retry, so a task doesn't run twice - Branch on
error.code, not the message. Retry 503 codes after a short wait - If you get
429 concurrency_limit_exceeded, put an idle session in standby to free its slot - Read a submission until it is
done,cancelledorfailed, then fetch the answer entry it names - Grant each agent only the tools it needs. Approvals and budgets are left to your application
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
Questions
Which is better for AI agents, Click or Crush?
Crush scores 53.3 (D) on agent readiness against Click's 48.6 (D), and leads in 4 of 7 scored categories. Click leads on schema & documentation and agent ergonomics.
Can an agent call Click and Crush without installing anything?
Click has a hosted endpoint at https://api.useclick.ai/v1. No hosted endpoint is listed for Crush.
Other comparisons with Click or Crush
- Agent Zero vs Click
- Agent Zero vs Crush
- Aider vs Click
- Aider vs Crush
- Amp vs Click
- Amp vs Crush
- Antigravity CLI vs Click
- Antigravity CLI vs Crush
- Auggie CLI vs Click
- Auggie CLI vs Crush
- AXLR vs Click
- AXLR vs Crush
- boxes.dev vs Click
- boxes.dev vs Crush
- Claude Code vs Click
- Claude Code vs Crush
- Click vs Cline
- Click vs Conductor
- Click vs Cursor CLI
- Click vs DeepSeek Harness (dsh)
- Click vs dsh-superagent (DeepSeek)
- Click vs Devin
- Click vs Droid CLI
- Click vs Pi
- Click vs Emdash
- Click vs Friday
- Click vs Gemini CLI
- Click vs GitHub Copilot CLI
- Click vs goose
- Click vs Harness²
- Click vs HarnessRouter
- Click vs Jules
- Click vs Junie CLI
- Click vs Kilo Code CLI
- Click vs Kimi Code CLI
- Click vs Kiro CLI
- Click vs Letta
- Click vs mini-swe-agent
- Click vs MiniMax Code
- Click vs Mistral Vibe CLI
- Click vs Muse Code
- Click vs OpenAI Agents API
- Click vs OpenAI Codex
- Click vs OpenCode
- Click vs OpenHands
- Click vs OpenMausBot
- Click vs Orca
- Click vs Paseo
- Click vs Prime Agent
- Click vs Qoder CLI
- Click vs Qwen Code
- Click vs Mirror CLI
- Click vs Rovo Dev CLI
- Click vs Sculptor
- Click vs T3 Code
- Click vs Traycer
- Click vs Unstoppable
- Click vs Verdent
- Click vs Vibe-Trading
- Click vs Warp (Warp Agent CLI and the Oz Agent API)
- 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
- Clawboo vs Crush
- CLI Manager vs Crush
- Crush vs Harness
- Crush vs herdr
- Crush vs Paperclip
- Crush vs Parallax
Machine-readable
- This page as Markdown
/compare/click-agents-vs-crush.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/click-agents.json·/api/v1/tools/crush.json - From a terminal
anchor compare click-agents crush(the CLI) - Over MCP
compare_tools {"a": "click-agents", "b": "crush"}at/mcp, no key