8 Best Kilo Code Alternatives (2026)

Most people searching for Kilo Code alternatives are not shopping — they already run it and something has stopped fitting. That something is usually a specific number rather than a feeling, so this page starts from the fields where Kilo Code genuinely trails the rosters it appears in, and only then covers the reasons that never show up in a table.

The measured reasons.

• Background agents — No. Claude Code records Yes.
• GitHub stars — 9,000, the weakest of the 9 here. Gemini CLI records 75,000.
• Opens PRs — No. Claude Code records Yes.

Any one of those is enough on its own if you sized your architecture around it. None of them is enough if you didn't — which is why the list is short and specific rather than a general case against Kilo Code.

The reasons that never make it into a table. A price rise after a funding round. A licence change that turns a self-host into a subscription. A region you now need and they do not have. An acquisition. A support experience that quietly degrades. None of those are fields, and all of them move teams — which is why every entry below links back to Coding agents, where the full field set and its sources live. The ones we catch get logged on the Kilo Code timeline.

How the shortlist is ordered. Every tool below shares at least one comparison category with Kilo Code, sorted by how many categories the two overlap in. There is no editorial ranking, no sponsorship and no affiliate link — the order is the overlap count, and the rationale under each is generated from the two tools' own cells, so it names real values rather than adjectives.

Aider — Minimal terminal pair-programmer with a tree-sitter repo map and automatic git commits. It meets Kilo Code in Coding agents. It is ahead on Headless / CI (Yes against Partial) and GitHub stars (37,000 against 9,000). What you give up: MCP (No, where Kilo Code records Yes) and Subagents (No, where Kilo Code records Yes). Best for scripted, repeatable edits where you want a git commit per change. Still the most auditable harness here, and the repo map is a better idea than much of what replaced it — but the project has visibly slowed while the category sprinted past on MCP, subagents and sandboxing. Pick it for minimalism, not for keeping up.

MCP

○NoKilo Code: Yes

Community-reported

Subagents

○NoKilo Code: Yes

Community-reported

Headless / CI

●YesKilo Code: Partial

Inferredverified 2026-01-15

Plan mode

◐PartialKilo Code: Yes

Inferred

Skills / commands

◐PartialKilo Code: Yes

Inferred

GitHub stars

37,000Kilo Code: 9,000

Community-reported

Amp — Sourcegraph's opinionated agent with no model picker and an ad-supported free tier. It meets Kilo Code in Coding agents. It is ahead on Token markup (Yes against No), Background agents (Partial against No) and Headless / CI (Yes against Partial). What you give up: BYOK (No, where Kilo Code records Yes) and Model breadth (no model choice, where Kilo Code records any provider / router). Best for teams who would rather not run a model-selection debate every quarter. Removing the model picker is a defensible product decision — most people choose badly and then blame the harness — but it means you control neither cost nor provider, and an ad-supported tier is an odd thing to sit next to a proprietary codebase. Subagent quality is genuinely good.

BYOK

○NoKilo Code: Yes

Inferredverified 2026-01-15

Model breadth

no model choiceKilo Code: any provider / router

Inferredverified 2026-01-15

Licence

proprietaryKilo Code: Apache-2.0

Inferredverified 2026-01-15

Token markup

●YesKilo Code: No

Inferred

Local models

○NoKilo Code: Yes

Inferredverified 2026-01-15

Pricing model

opaque creditsKilo Code: BYOK tokens only

Vendor-claimedsource

Claude Code — Anthropic's terminal-first agent, with IDE, web and GitHub Action surfaces. It meets Kilo Code in Coding agents. It is ahead on Opens PRs (Yes against No), Background agents (Yes against No) and Permissions (allowlist + OS sandbox against granular allowlist). What you give up: Licence (proprietary, where Kilo Code records Apache-2.0) and Local models (No, where Kilo Code records Yes). Best for terminal-native teams who want subagents and hooks without building them. The most complete extensibility surface of any harness here — subagents, hooks, skills and MCP all first-class — at the cost of being locked to one model vendor. If Anthropic's pricing or availability is a business risk for you, that lock is the whole argument against it.

Opens PRs

●YesKilo Code: No

Vendor-claimedsource

Background agents

●YesKilo Code: No

Vendor-claimedsource

Licence

proprietaryKilo Code: Apache-2.0

Inferredverified 2026-01-15

Local models

○NoKilo Code: Yes

Community-reported

Permissions

allowlist + OS sandboxKilo Code: granular allowlist

Vendor-claimedverified 2026-01-15source

Model breadth

one vendor + custom endpointKilo Code: any provider / router

Vendor-claimedsource

Cline — Open-source VS Code and JetBrains agent built around an explicit plan/act split. It meets Kilo Code in Coding agents. It is ahead on GitHub stars (50,000 against 9,000). What you give up: Subagents (No, where Kilo Code records Yes) and Repo indexing (agentic grep, where Kilo Code records embeddings index). Best for VS Code and JetBrains teams who want BYOK without leaving the IDE. The plan/act split remains the clearest interaction model in the category — you approve an approach, not a diff. It is the safest default for VS Code teams who want BYOK, but it stays inside the editor: no subagents, no hooks, no PR path.

Subagents

○NoKilo Code: Yes

Community-reported

Repo indexing

agentic grepKilo Code: embeddings index

Community-reported

GitHub stars

50,000Kilo Code: 9,000

Community-reported

Codex CLI — OpenAI's open-source Rust agent, with the strongest local sandboxing on this page. It meets Kilo Code in Coding agents. It is ahead on Opens PRs (Yes against No), Background agents (Yes against No) and Permissions (allowlist + OS sandbox against granular allowlist). What you give up: Subagents (No, where Kilo Code records Yes) and Model breadth (one vendor + custom endpoint, where Kilo Code records any provider / router). Best for unattended local runs where a real OS sandbox is non-negotiable. The best containment story of any local harness — Seatbelt and Landlock are real boundaries, not an allowlist with good marketing. Weaker than Claude Code on orchestration primitives: no subagents, notification-only hooks, thinner custom-command support.

Opens PRs

●YesKilo Code: No

Inferredverified 2026-01-15

Subagents

○NoKilo Code: Yes

Community-reported

Background agents

●YesKilo Code: No

Inferredverified 2026-01-15

Permissions

allowlist + OS sandboxKilo Code: granular allowlist

Vendor-claimedverified 2026-01-15source

Model breadth

one vendor + custom endpointKilo Code: any provider / router

Vendor-claimedverified 2026-01-15source

Repo indexing

agentic grepKilo Code: embeddings index

Community-reported

Cursor — VS Code fork with a real codebase index, background cloud agents and a CLI. It meets Kilo Code in Coding agents. It is ahead on Opens PRs (Yes against No), Background agents (Yes against No) and Token markup (Partial against No). What you give up: Licence (proprietary, where Kilo Code records Apache-2.0) and Local models (No, where Kilo Code records Yes). Best for large monorepos where agentic grep runs out of context before it finds anything. A real persistent codebase index inside the editor you review in, which is exactly what a million-line monorepo needs and what grep-based harnesses cannot fake. It is not the only index here — Windsurf and Kilo Code embed too, and Copilot and Devin read an index alongside live search — but it is the best-integrated one. You pay for it in lock-in: the index, the gateway and the agent identity are all Cursor's, and BYOK is a second-class path.

Opens PRs

●YesKilo Code: No

Inferredverified 2026-01-15

Background agents

●YesKilo Code: No

Inferredverified 2026-01-15

Licence

proprietaryKilo Code: Apache-2.0

Inferredverified 2026-01-15

Local models

○NoKilo Code: Yes

Inferred

Token markup

◐PartialKilo Code: No

Community-reported

Permissions

allowlist + OS sandboxKilo Code: granular allowlist

Community-reported

Devin — Fully delegated cloud engineer: file a task in Slack or the web app, get a PR back. It meets Kilo Code in Coding agents. It is ahead on Opens PRs (Yes against No), Background agents (Yes against No) and Token markup (Yes against No). What you give up: BYOK (No, where Kilo Code records Yes) and Subagents (No, where Kilo Code records Yes). Best for backlogs of small, well-specified tickets nobody wants to pick up. The clearest expression of full delegation: no local client, no model picker, a pull request or nothing. A real fit for well-specified tickets on a repo with good tests, and a poor one for anything exploratory. ACU pricing means you learn the cost afterwards.

Opens PRs

●YesKilo Code: No

Inferredverified 2026-01-15

BYOK

○NoKilo Code: Yes

Inferredverified 2026-01-15

Subagents

○NoKilo Code: Yes

Inferred

Background agents

●YesKilo Code: No

Inferredverified 2026-01-15

Model breadth

no model choiceKilo Code: any provider / router

Inferred

Checkpoint & undo

○NoKilo Code: Yes

Inferred

DIY harness — Your own loop over a model API with an agent SDK — the build-it-yourself reference point. It meets Kilo Code in Coding agents. It is ahead on Opens PRs (Partial against No), Background agents (Partial against No) and Headless / CI (Yes against Partial). What you give up: Plan mode (No, where Kilo Code records Yes) and Checkpoint & undo (No, where Kilo Code records Yes). Best for one repeated task with a known shape and a tight tool surface. Right for narrow, repeated jobs — a codemod runner, a test-backfill bot — where a general harness wastes most of its context rediscovering conventions you could have hardcoded. Wrong for open-ended engineering, where you will spend a quarter rebuilding permissions, checkpointing and context management worse than the incumbents. Note that we carry DIY harness as the do-it-yourself baseline in that roster — the "what if we just ran this ourselves" reference point. The honest answer is usually that it is cheaper and considerably more work.

Plan mode

○NoKilo Code: Yes

Inferred

Checkpoint & undo

○NoKilo Code: Yes

Inferred

Skills / commands

○NoKilo Code: Yes

Inferred

Repo indexing

manual context onlyKilo Code: embeddings index

Inferred

Opens PRs

◐PartialKilo Code: No

Inferred

Background agents

◐PartialKilo Code: No

Inferred

There is no editorial ranking on this page and no sponsorship behind it. The order is mechanical: every tool that shares a comparison category with Kilo Code, sorted by how many categories the two overlap in. A tool that meets Kilo Code in three rosters sits above one that meets it in a single roster, because more overlap means the comparison is more like-for-like.

The rationale under each entry is composed from the two tools' own cells. Where they differ on a field we score, the sentence names both values and the unit. Where they don't differ, it says so instead of manufacturing a distinction — which is why some entries are short.

Values, sources and verification dates all live on the category tables: Coding agents. If a figure here disagrees with a vendor's current pricing page, the vendor is right and we are stale.

Still deciding whether to move at all? The Kilo Code profile has the when-to-use and when-not-to-use blocks, and the Kilo Code timeline has the dated changes that usually trigger a migration.