Skip to content
hubai.uk Ask HubAI
Menu
HUBAI NAVIGATOR

Start with the decision.

Build my AI stack
FIND YOUR FITAsk HubAITell us the job. Find tools that fit your budget and team.Start decision
FREE AI TOOL DESK

Free Code AI tools and trials.

Find a route for a small test before committing budget. These are recorded free plans, trials, credits or public tools. Confirm current allowances and eligibility at the provider. Candidates are alphabetical, not a performance ranking.

Before the first uploadUse approved, non-sensitive sample work. Decide what a usable result must contain and record any corrections.Full buying guide
Code AI

Anthropic OSS Scanner

Useful to inspect for maintainer-owned vulnerability triage for accepted open-source projects.

Recorded entry: Case-by-case admission; no guaranteed UK acceptance.Watch-out: Independent same-task test pending

Profile check: 9 October 2026. Official product source

Model AI

Cognition SWE-2

Useful to inspect for cost-aware agentic coding as a standalone devin model or the execution sidekick in devin fusion.

Recorded entry: Devin Free has limited model availability; paid plans provide full model accessWatch-out: Promotional access ends on a published date and future terms are not guaranteed

Profile check: 13 September 2026. Official product source

Code AI

Devin Fusion

Useful to inspect for engineering teams testing a frontier lead and lower-cost sidekick on long, repository-level coding work.

Recorded entry: Free plan has a light quota and limited models; paid plans include full model access, with promotional SWE-2 use through 10 October 2026Watch-out: Two-agent orchestration adds failure paths and makes spend attribution more complex

Profile check: 13 September 2026. Official product source

Code AI

GitHub Copilot

Useful to inspect for mainstream coding assistance across ides, github and controlled desktop workflows.

Recorded entry: Trial may applyWatch-out: Local sandboxing is off by default and remains in public preview

Profile check: 3 October 2026. Official product source

Model AI

GPT-6 Luna

Useful to inspect for high-volume extraction, classification, transformation and first-pass agent work that needs low token cost and a large context window.

Recorded entry: Metered API access; gradual rollout through ChatGPT Work, Codex and eligible GitHub Copilot plans, with Luna desktop access announced for Free and Go usersWatch-out: Lower token price is not evidence of adequate task quality or lower complete cost

Profile check: 23 September 2026. Official product source

Model AI

Grok 4.7

Useful to inspect for long-context coding, agentic tool use and knowledge work where teams can run a controlled same-task evaluation.

Recorded entry: Grok Build has a free starting route; public API use is metered. GitHub Copilot access requires an eligible paid plan and is rolling out graduallyWatch-out: Benchmark, speed and safety results are provider-reported

Profile check: 22 September 2026. Official product source

TEST THIS WORKFLOW

Checks for code ai.

  1. Check repository access, secrets and tool permissions
  2. Require passing tests and a reviewable diff
  3. Measure accepted changes and developer correction time
Does free entry cover the whole workflow?

No. A free chat plan, trial, credit allowance or public calculator is a specific entry route. Exports, API use, team controls, commercial rights and connected services need separate checks.

When is upgrading justified?

Run the same work at the expected volume and record accepted output, retries, reviewer time and the first paid restriction. Upgrade when the additional capability solves an observed need. Estimate complete cost with your own assumptions.

What if I need to replace an existing tool?

Check whether a second product adds a missing capability before migrating files, prompts, integrations and seats. Review switching candidates and keep the current workflow available until the replacement passes your acceptance checks.