Toolbox/Coding agents

IDE & editor agents

IDE or editor extension agent

13 repositories, most starred first
State of the category

org2AI/ORG2 org2AI/ORG2 is the clear leader by adoption and capability; it delivers persistent, replayable agent sessions, cross‑session memory and audit trails so teams can review and attribute agent actions. If you don't need team-level replay/auditability, pick a specialist project for UI, editor integration, local hosting, spec-driven QA, or cost/context efficiency instead.

Replay & Audit Trails
Teams that share workflows or operate in regulated/safety‑sensitive environments need durable, inspectable agent histories and accountability features so actions can be reviewed and traced.
Visual Multi-Agent UIs
Product and engineering teams frequently prefer a visual workspace to run multiple agents in parallel, review edits as red/green diffs, and manage sessions rather than a single chat interface.
Editor & Domain Integrations
Organizations working in specific editors or domains (game engines, Emacs, knowledge‑vaults) need native integrations and plugins so agents operate directly in their existing workflows.
Spec-driven QA
Teams that require enforceable requirements, testable specs and quality gates need agent tooling that generates, verifies and enforces specs and tests instead of freeform code edits.
Context & Cost Efficiency
Projects constrained by model context windows or API/tool‑call costs need mechanisms to prune context, chain follow‑ups inside single tool calls, and maximize value from limited quotas.
Find your fit

Which one matches your setup?

Answer any of the questions — the shortlist updates as you go. Recommendations come from the capability passports below, nothing else.

Where should reviews happen?
Can code leave your infrastructure?
What matters most?
Model access?
Pick at least one answer to get a shortlist.
Side by side

Comparison matrix

Axes are extracted from each project's docs by our review pipeline; the maturity score is computed from stars, growth and commit activity — not an opinion. Click a column to sort.

Runs inModelsContextCost to run
2.6k
CLIIDEBYOKWhole-repo analysisReviewable outputsSelf-hostableUses your API key (provider billing applies)
2.6k
CLIIDEBYOKWhole-repo analysisReview controlsSelf-hostableYour API keys; free desktop app
1.6k +50/7d
IDEOpenAIAnthropicFixed providerMulti-file workspaceApprove/reject reviewCloud-connected desktopFree desktop app; external model API costs may apply
864 +2/7d
IDEBYOKOpenAIOllama / localFixed providerWhole-repo analysisApproval & reviewSelf-hostableFree local preview; provider charges apply for BYOK/hosted models
168 +14/7d
Coding-agent pluginIDECLIFixed providerDiff + related filesQuality gatingSelf-hostableFree, local install
895 +6/7d
IDECLICoding-agent pluginAnthropicProject-wideConfigurable tools & permsAnthropic cloud via CLIRequires Anthropic (Claude) account / subscription
584
IDECoding-agent pluginFixed providerWorkspace contextSession controlsFully localFree; requires local agent runtime
275 +3/7d
IDECLIOpenAIAnthropicGeminiFixed providerDiff + related filesBasic config filtersCloud APIs (user key)Varies by backend (cloud API or local CLI)
64
IDECLIAnthropicOpenAIGeminiBYOKCross-file explorationDedup & guardrailsAPI key / OAuthUse your provider subscription via OAuth or an API key (OpenRouter supported)
61
Web appIDEBYOKOpenAIAnthropicWhole-repo indexEvidence & gatingHosted demo + localFree demo; may use external model APIs / your API key
855
IDECoding-agent pluginWeb appBYOKSession-onlyNoneAgent cloud dependentUses your agent's tool-call quota
477 +1/7d
IDECLIBYOKOpenAIAnthropicGeminiOllama / localWhole-repo accessApproval gatesSelf-hostableYour API key for cloud models; local/self-hosted models supported.
Ranked by maturity — 1 more in the full catalog below.
At a glance

Capability profiles

Six axes, 0–5 each. The shape tells you the strategy: a wide hexagon is a generalist, a spike is a specialist. Showing the 8 most established — the rest are in the full catalog.

yorgai/ORG22.6k
ContextNoiseCustomPrivacyModelsMaturity

Provides persistent, replayable agent trajectories, cross-session memory, and AI-blame for team-level review and accountability that typical IDE agents do not offer.

org2AI/ORG22.6k
ContextNoiseCustomPrivacyModelsMaturity

Provides replayable, inspectable agent trajectories, cross-session memory, and AI-blame for team review and accountability—capabilities not offered by typical stateless AI IDEs.

ContextNoiseCustomPrivacyModelsMaturity

A visual WYSIWYG workspace that runs multiple coding agents in parallel and lets you review and approve their edits as red/green diffs while managing sessions and tasks.

ContextNoiseCustomPrivacyModelsMaturity

A durable, local-first agentic IDE that preserves task workspace and history across sessions while exposing explicit approval and review surfaces for sensitive actions.

ContextNoiseCustomPrivacyModelsMaturity

Provides agentic skills that enforce spec-driven discovery, testable requirements, design alternatives, and quality-gated execution inside coding agents—something generic coding assistants do not enforce.

ContextNoiseCustomPrivacyModelsMaturity

Native Unreal Engine 5.7 editor integration that exposes a dynamic UE5.7 context loader and a 20+ tool MCP bridge to Claude Code for direct Blueprint, asset, and level manipulation.

ContextNoiseCustomPrivacyModelsMaturity

Unifies multiple local agent runtimes into a single VS Code chat sidebar with workspace-aware chat and rich animation/customization controls.

ContextNoiseCustomPrivacyModelsMaturity

Provides a uniform, backend‑agnostic Emacs interface and workflow so you can switch between many AI CLIs without changing your editor experience or prompts.

All repositories (13)

System of record for how agents build software: Built-in rust harness & 20+ CLIs.

2.6k
-107d
TypeScript
3 mo

System of record for how agents build software: Built-in rust harness & 20+ CLIs.

2.6k
-107d
TypeScript
3 mo

Nimbalyst - The open-source visual workspace for Claude Code, Codex, and OpenCode. Run multiple coding agents…

1.6k
+507d
TypeScript
10 mo

Claude Code CLI integration for Unreal Engine 5.7 - Get AI coding assistance with built-in UE5.7 documentation…

895
+67d
C++
8 mo

Local-first, zero-trust agentic IDE for verifiable autonomous software development.

864
+27d
TypeScript
1 mo

10x-Tool-Calls is a lightweight rules file designed to help you maximize the value of your monthly AI coding t…

855
Python
1 yr

VS Code chat sidebar for local AI coding agents

584
TypeScript
2 mo

IDE, A native-feeling AI coding workspace that blends chat, planning, agent execution, and project navigation…

477
+17d
TypeScript
5 mo

Unified Emacs interface supporting OpenAI Codex, Antigravity CLI, Claude Code, GitHub Copilot CLI, Opencode,…

275
+37d
Emacs Lisp
1 yr

OpenSpec Plus — Agentic skills that enhance OpenSpec's Spec-Driven Development through better discovery, requi…

168
+147d
2 mo

A vault-specific agent equipped with agentic capacity, fast search, flexible commands, vault management, and t…

86
TypeScript
1 yr

Agentic IDE with custom harness

64
Rust
3 mo

Benzi is AI-native code intelligence infrastructure. Claude Code greps; Cursor embeds; Aider maps signatures;…

61
Python
1 mo
Don't want to self-host?

Hosted alternatives

If running your own reviewer is more ops than you want, these managed services cover the same job.

Cursor

The managed AI-first editor: the agent, model access and indexing come on a subscription, so there is nothing to self-host or wire to a provider.

Try Cursor
Windsurf

Codeium's agentic editor with the coding agent built in and hosted, an alternative to bolting an open-source agent onto your own editor setup.

Try Windsurf
GitHub Copilot

Managed in-editor assistance and agent mode across the major IDEs on a subscription, run against GitHub's models rather than a harness you install and configure.

Try GitHub Copilot

More in Coding agents