AnyFrame
Workflow & Automation · tested 2026-08-31 · re-test due 2026-11-29 · by the Hlido desk, not the vendor
In short: A harness-agnostic platform for spinning up team agents inside Slack/Linear/GitHub — a clean concept and real SDK, but visibly pre-traction and crowded on differentiation.
5 PASS · 0 FAIL of 5 public-surface claims
Quick answer
AnyFrame scores 71/100 (STEADY) on Hlido’s independent, hands-on test (reviewed 2026-08-31). STEADY (71) for a coherent concept (harness-agnostic team agents triggered in existing tools), a real SDK/API surface, and a low-friction free trial. Pricing: Open source · Usage-based · Free tier (free entry point documented).
AnyFrame's bet is that teams do not want to marry one coding harness: you build a named, sandboxed agent, bind it to a template and a runtime, and swap between Claude Code, Cursor, Codex or OpenCode without changing everything else. It triggers where people already work — a Slack message, a Linear ticket, a PR comment — and it ships an SDK ('pip install anyframe', TypeScript too) so agents can be created and run in a few lines. The harness-swappability and the trigger-where-you-work framing are the genuinely appealing ideas, and the free-to-try model (500 credits, no card) lowers the bar to evaluate. The caution flags are equally clear from the public surface: the product looks early — the in-page dashboard literally shows 'No agents yet', self-hosting is 'coming soon', and several of the flagship behaviours (browser 'hands and eyes', describe-and-preview) are shown as demos rather than proven; and the category is crowded, so 'any agent, any team, any tool' reads more as positioning than as a demonstrated moat. Worth watching, but this is an early platform to trial, not yet infrastructure to standardise on.
Why STEADY
STEADY (71) for a coherent concept (harness-agnostic team agents triggered in existing tools), a real SDK/API surface, and a low-friction free trial. Held near the band floor because the public surface shows a pre-traction product (empty dashboard, self-hosting "coming soon", demo-shown flagship features) in a crowded space where the differentiation is asserted rather than demonstrated.
Public-surface checklist
- PASS Homepage loads (required)
- PASS Primary value prop (required) — 'Platform for every agent your team builds' — harness-agnostic team agents
- PASS Cta present (required) — 'Start Building' / 'Book a demo'
- PASS Pricing or access — 500 free credits, no card; pay-as-you-go after (FAQ)
- PASS Evidence or demo — Interactive demos + SDK snippet; flagship features shown as demos
What we saw
4 screenshots captured by the Hlido engine during the reviewed run (run-b4f6b44f010a8013-anyframe-dev). Our own captures — not vendor marketing material.
What it does well
- Harness-agnostic by design — swap Claude Code / Cursor / Codex / OpenCode without re-tooling
- Triggers inside existing workflows (Slack, Linear, GitHub PR/issue comments)
- Real programmatic surface: Python and TypeScript SDKs to create and run agents in a few lines
- Low-friction evaluation: 500 free credits, no credit card, pay-as-you-go after
- Clear, honest FAQ (sandbox isolation, human-approval gating for risky/production actions)
What it fails at
- Visibly early: the in-product dashboard shows "No agents yet"; self-hosting/open-source is "coming soon"
- Flagship capabilities (browser "hands and eyes", describe-and-preview) are presented as demos, not proven outcomes
- Differentiation is asserted ("any agent, any team, any tool") in a crowded category without a demonstrated moat
- No public reliability, security, or track-record evidence on the surface
Red flags
- Product appears pre-traction (empty dashboard state, "coming soon" self-hosting) while marketing implies breadth — evaluate before depending on it
Best for
- Teams wanting to trial agents inside Slack/Linear/GitHub without committing to a single harness
- Developers who want to script agent creation/runs via an SDK
- Early adopters comfortable evaluating a pre-1.0 platform
Not recommended for
- Teams needing self-hosting or an on-prem story today (not yet available)
- Buyers who need proven reliability before standardising on a platform
- Anyone wanting a clearly differentiated, battle-tested orchestration layer now
Pricing & access
- ModelOpen source · Usage-based · Free tier
- Free entry pointYes — a free tier or open-source edition is documented
- Pricing findable on the public surfacePASS 500 free credits, no card; pay-as-you-go after (FAQ) (tested 2026-08-31)
Derived from Hlido-held evidence only (engine checklist + editorial text); quotes are verbatim from the scorecard; not vendor-supplied; re-derived daily. Verify current prices on the vendor's pricing page. Last verified 2026-08-31.
Related agents
Agent relevance
API Webhook SDK
Agentic-Commerce Readiness 54/100 · INTEGRABLE
Independent readiness for agent delegation & transaction. How it’s scored · check live
Moderate-to-strong intent: Python/TypeScript SDKs and event triggers (Slack/Linear/GitHub) let agents be created and driven programmatically. Not behaviourally verified by Hlido; the product surface indicates an early stage.
Agent-friendly score: 6/10
Score over time
The longitudinal record — every point is the score as published on that date. Raw series.
Evidence
- Harness-agnostic agents (Claude Code, Cursor, Codex, OpenCode), swappable — source (2026-08-31) verified
- Triggered from Slack, Linear, GitHub; Python & TypeScript SDKs — source (2026-08-31) verified
- Free to try: 500 credits, no card required, pay-as-you-go after — source (2026-08-31) verified
- Self-hosting / open-source version — source (2026-08-31)
scorecard.json · transparency passport · registry · methodology
Embed this trust badge
Markdown
[](https://hlido.eu/check/?agent=anyframe)HTML
<a href="https://hlido.eu/check/?agent=anyframe"><img src="https://hlido.eu/badge/anyframe.svg" alt="Hlido trust score"></a>