Hacker ApprovedDepartments

Continue

Ranked 17 of 41 coding agents by recommenders

Open-source AI coding assistant people recommend for its configurable checks, autocomplete, and local model support with Ollama. Common caveat: many reports of buggy plugin behavior in VS Code and JetBrains.

Open-source AI coding assistant people recommend for its configurable checks, autocomplete, and local model support with Ollama. Common caveat: many reports of buggy plugin behavior in VS Code and JetBrains.

30 people gave an opinion

recommend it
18
criticize it
12
approval share
60%
Each figure is one person. RecommendsCriticizes

Recommended in 6 of 13 months

  1. November 2025: recommended
  2. December 2025: not recommended
  3. January 2026: not recommended
  4. February 2026: recommended
  5. March 2026: not recommended
  6. April 2026: recommended
  7. May 2026: recommended
  8. June 2026: recommended
  9. July 2026: not recommended
  10. August 2026: recommended
  11. September 2026: not recommended
  12. October 2026: not recommended
  13. November 2026: not recommended (month in progress)

Why it doesn’t carry the badge

  • 18 people recommend itNeeds 10 or more, met.
  • 1.5 recommenders for every criticNeeds 2 to 1 or better, not met.
  • Recommended in 6 of 13 monthsNeeds 4 or more, met.

The same three rules apply to every product, and the badge can’t be bought. How the badge works

What people say about it

The reasons people give, with the number of comments that give each one. Open a reason to read what they said.

Why people recommend it

Each mark is one comment

  • Configurable, focused checks product

    “Continue is very focused on the use case of checks and gets a lot of the small details right”

    Comment from 17 Feb 2026 in “Show HN: Continue – Source-controlled AI checks, enforceable in CI”

    “our checks product is powered by an open-source CLI (we think this is important)”

    Comment from 17 Feb 2026 in “Show HN: Continue – Source-controlled AI checks, enforceable in CI”

    “the configurable part turns out to be the main bit”

    Comment from 17 Feb 2026 in “Show HN: Continue – Source-controlled AI checks, enforceable in CI”
  • Works in VS Code and VSCodium

    “Continue on vscode with Ollama running (start it with "ollama serve") is great.”

    Comment from 31 May 2026 in “Bye Bye Copilot – new pricing looks to be a joke”

    “The Continue plugin for VSCode gets all of this accomplished.”

    Comment from 31 May 2026 in “Bye Bye Copilot – new pricing looks to be a joke”

    “help you code on vscodium with Continue. Pretty nice!”

    Comment from 4 May 2026 in “Usage-based pricing killing your vibe, here's how to roll your own local AI”
  • Works with local models like Ollama

    “Continue on vscode with Ollama running (start it with "ollama serve") is great.”

    Comment from 31 May 2026 in “Bye Bye Copilot – new pricing looks to be a joke”

    “It’s the only one that handles air-gapped setups properly.”

    Comment from 9 Apr 2026 in “Best Open Source Offline AI Agent”
  • Good autocomplete

    “I've also made decent experiences with continue, at least for autocomplete.”

    Comment from 4 Feb 2026 in “Claude Code: connect to a local model when your quota runs out”

    “best open source autocomplete in our view”

    Comment from 24 Nov 2025 in “Sunsetting Supermaven”

What people warn about

Each mark is one comment

  • Buggy, janky plugin behavior

    “most of the plugins that try to do that are pretty buggy or broken (e.g. Continue.dev)”

    Comment from 27 Dec 2025 in “Show HN: Mysti – Claude, Codex, and Gemini debate your code, then synthesize”

    “i tried the continue vscode extension, and it seemed kind of janky”

    Comment from 27 Apr 2026 in “GitHub Copilot is moving to usage-based billing”

    “the whole plugin was a buggy mess and it didn't work well”

    Comment from 5 Jan 2026 in “I switched from VSCode to Zed”
  • Frustrating experience in JetBrains and VS Code

    “that experience was a mess both in JetBrains IDEs, as well as Visual Studio Code”

    Comment from 22 Jan 2026 in “Show HN: Sweep, Open-weights 1.5B model for next-edit autocomplete”

    “a lot of frustration with the Continue plugin in my IDE”

    Comment from 25 Jun 2026 in “Computer use in Gemini 3.5 Flash”
  • Ignores instructions and burns tokens

    “even tho I told it no changes without my explicit go ahead, it ignored me.”

    Comment from 13 Mar 2026 in “Shall I implement it? No”

    “8M token burned in 30 minutes. App does not work.”

    Comment from 21 Jun 2026 in “Building Reliable Agentic AI Systems”

Other coding agents people recommend

The four most recommended other coding agents, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.

Continue compared with 4 alternatives
ProductRecommendCriticizeApprovalMonthsOwnedBadge
GitHub Copilot57199337%121 yr46 owners—
oh-my-pi1042879%92 mo5 ownersApproved
Grok Build CLI6611437%6——
DeepSeek Harness632869%41 mo5 ownersApproved
ContinueThis page181260%6——
See all 41 coding agents, ranked

What people said

36 of the 40 comments that mention it, newest first. Each links to the original comment.

“Swapped Continue for Kilo Code.”

CriticizesComment from 3 Sep 2026 in “ChatGPT outage – Resolved”

“There is the obvious alternative of still using it, including creating your own fork.”

RecommendsComment from 22 Aug 2026 in “Continue coding agent is dead. Alternatives?”

“"Continue" (the vscode extension) worked horribly”

CriticizesComment from 25 Jul 2026 in “Open-weight AI is having its Kubernetes moment. Let's not ruin it”

“a lot of frustration with the Continue plugin in my IDE”

CriticizesComment from 25 Jun 2026 in “Computer use in Gemini 3.5 Flash”

“8M token burned in 30 minutes. App does not work.”

CriticizesComment from 21 Jun 2026 in “Building Reliable Agentic AI Systems”

“it exited its funding round to the Titler octopus”

CriticizesComment from 17 Jun 2026 in “Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?”

“I think Continue is the biggest yc one.”

RecommendsComment from 16 Jun 2026 in “SpaceX to buy Cursor AI coding agent operator Anysphere for $60B”

“Continue helped but its now part of Cursor”

MixedComment from 16 Jun 2026 in “SpaceX to buy Cursor AI coding agent operator Anysphere for $60B”

“Continue on vscode with Ollama running (start it with "ollama serve") is great.”

RecommendsComment from 31 May 2026 in “Bye Bye Copilot – new pricing looks to be a joke”

“The Continue plugin for VSCode gets all of this accomplished.”

RecommendsComment from 31 May 2026 in “Bye Bye Copilot – new pricing looks to be a joke”

“It recommended the Continue plugin for VSCode.”

RecommendsComment from 23 May 2026 in “Microsoft Drops Claude Code After Budget Overrun”

“checked if Cursor and Continue.dev have the same startsWith parsing issue. They do.”

CriticizesComment from 23 May 2026 in “I reproduced a Claude Code RCE. The bug pattern is everywhere”

“put Aider/Continue/Cline in front of it”

MixedComment from 13 May 2026 in “Show HN: AICTL – A native AI agent for terminal and macOS, in Rust”

“help you code on vscodium with Continue. Pretty nice!”

RecommendsComment from 4 May 2026 in “Usage-based pricing killing your vibe, here's how to roll your own local AI”

“i tried the continue vscode extension, and it seemed kind of janky”

CriticizesComment from 27 Apr 2026 in “GitHub Copilot is moving to usage-based billing”

“It’s the only one that handles air-gapped setups properly.”

RecommendsComment from 9 Apr 2026 in “Best Open Source Offline AI Agent”

“if you've used opencode/continue-dev”

MixedComment from 8 Apr 2026 in “I've Sold Out”

“kind of broken regardless of models”

CriticizesComment from 16 Mar 2026 in “Ask HN: How is AI-assisted coding going for you professionally?”

“even tho I told it no changes without my explicit go ahead, it ignored me.”

CriticizesComment from 13 Mar 2026 in “Shall I implement it? No”

“they generated crap that's unmaintainable long term”

CriticizesComment from 2 Mar 2026 in “AICode: A VSCode methodology for long-term maintainable AI coding”

“I can imagine this would be very useful.”

RecommendsComment from 19 Feb 2026 in “Show HN:`npx continues` – resume same session Claude, Gemini, Codex when limited”

“this is exactly what i needed”

RecommendsComment from 19 Feb 2026 in “Show HN:`npx continues` – resume same session Claude, Gemini, Codex when limited”

“it's been working very well for me”

RecommendsComment from 19 Feb 2026 in “Show HN:`npx continues` – resume same session Claude, Gemini, Codex when limited”

“Continue is very focused on the use case of checks and gets a lot of the small details right”

RecommendsComment from 17 Feb 2026 in “Show HN: Continue – Source-controlled AI checks, enforceable in CI”

“the configurable part turns out to be the main bit”

RecommendsComment from 17 Feb 2026 in “Show HN: Continue – Source-controlled AI checks, enforceable in CI”

“our checks product is powered by an open-source CLI (we think this is important)”

RecommendsComment from 17 Feb 2026 in “Show HN: Continue – Source-controlled AI checks, enforceable in CI”

“We saw this play out beautifully with amp, kilo, roo, cline, continue”

RecommendsComment from 6 Feb 2026 in “Claude Code Agent Teams”

“I've also made decent experiences with continue, at least for autocomplete.”

MixedComment from 4 Feb 2026 in “Claude Code: connect to a local model when your quota runs out”

“easy to try out and see if it meets your needs”

RecommendsComment from 4 Feb 2026 in “Claude Code: connect to a local model when your quota runs out”

“that experience was a mess both in JetBrains IDEs, as well as Visual Studio Code”

CriticizesComment from 22 Jan 2026 in “Show HN: Sweep, Open-weights 1.5B model for next-edit autocomplete”

“the whole plugin was a buggy mess and it didn't work well”

CriticizesComment from 5 Jan 2026 in “I switched from VSCode to Zed”

“most of the plugins that try to do that are pretty buggy or broken (e.g. Continue.dev)”

CriticizesComment from 27 Dec 2025 in “Show HN: Mysti – Claude, Codex, and Gemini debate your code, then synthesize”

“Continue.dev autocomplete sucks and is buggy (Ollama)”

CriticizesComment from 22 Dec 2025 in “A guide to local coding models”

“VC funded startups who's main plan is likely an acquisition”

CriticizesComment from 15 Dec 2025 in “Ask HN: What Are You Working On? (December 2025)”

“best open source autocomplete in our view”

RecommendsComment from 24 Nov 2025 in “Sunsetting Supermaven”

“Isn't Continue supposed to help you do that, in VSCode?”

RecommendsComment from 5 Nov 2025 on Hacker News

Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.