Aide by CodeStory

Aide is an open-source AI-first code editor built by CodeStory. It's a fork of VS Code with a companion runtime called Sidecar that runs an autonomous coding agent on your machine. Rather than only responding to chat prompts, Aide can be given a high-level goal — 'add SSO to the login flow', 'migrate this package to Zod v4' — and it will explore the repo, plan a set of edits, apply them across files, run tests, and self-correct. Because Sidecar is local, it can index your codebase, watch file changes, and drive the editor UI in ways that a pure server-side agent cannot. Aide supports Anthropic Claude, OpenAI, Gemini, and open models via OpenRouter, and it inherits the full VS Code extension ecosystem so your existing linters, formatters, debuggers, and language servers still work. The core is source-available, and CodeStory offers a hosted plan with pooled model credits for teams that don't want to manage API keys. Aide is a good fit for engineers who liked Cursor's ambition but want a more agent-forward, more open, and more customizable base — and who don't mind installing a separate binary alongside the editor.

Practical assessment

Aide by CodeStory should be judged by the workflow it replaces, not by a long list of AI claims. Start with one bounded, reversible job drawn from real work. Define success in advance: elapsed time, manual corrections, successful completion across five to ten repeated attempts, and the quality of the final deliverable. For coding and operations tools, run tests, inspect every proposed change, and log tool calls. For business systems, use a sandbox or read-only account and confirm that permissions match each user's role. This turns a polished demonstration into evidence a buyer can trust.

The product's concrete capabilities include AI-native VS Code fork with an autonomous agent runtime (Sidecar); Repository-wide planning and multi-file edits; Local codebase indexing for privacy-friendlier context; Model-agnostic: Claude, GPT, Gemini, OpenRouter; Compatible with the VS Code extension ecosystem; Deterministic tool-use with edit approvals. Those features matter when they remove a recurring bottleneck, but they do not eliminate normal engineering or operational discipline. Test failure recovery, exports, rate limits, collaboration, audit logs, and behavior with incomplete inputs. Ask which models or external services process data, where data is stored, how long it is retained, and whether customer content is used for training.

Pricing recorded in the source is: Free (BYO Key): $0; CodeStory Cloud: Paid. Treat these figures as planning guidance rather than a quote. The homepage and pricing endpoint returned no usable content during this research run, so current prices, quotas, and packaging need manual confirmation. Never fill an unknown price with an estimate. Total cost should include seats, usage credits or API charges, infrastructure, onboarding, support, and expert review time. Open-source software can remove license fees while still creating hosting and maintenance costs.

Strengths, limits, and fit

Provides aI-native VS Code fork with an autonomous agent runtime (Sidecar), a concrete advantage for teams that need this workflow. Provides repository-wide planning and multi-file edits, a concrete advantage for teams that need this workflow. Provides local codebase indexing for privacy-friendlier context, a concrete advantage for teams that need this workflow. Provides model-agnostic: Claude, GPT, Gemini, OpenRouter, a concrete advantage for teams that need this workflow. Limitations include Current vendor pricing and plan limits could not be independently verified because the site returned no usable HTML. Adoption requires a realistic pilot because behavior may differ by plan, deployment, or connected service. Automated output still needs human review, narrow permissions, and a tested recovery path. Total cost may include implementation, training, model usage, hosting, and support beyond the license price. Choose Aide by CodeStory when its capabilities address a measured pain point and the team can govern the access it needs. Avoid broad rollout when a pilot cannot reproduce results, users cannot export work, or required permissions exceed the value of the automation.

Relevant alternatives include aider, cursor agent, visual studio code, continue dev. Compare the same end-to-end task in each product with identical inputs and criteria. Record setup time, successful runs, corrections, latency, and cost. Test a partial failure halfway through a task. The best option is usually the one that fails visibly, preserves user control, and makes recovery straightforward—not simply the one with the most impressive first result.