Sourcegraph Cody
SourcegraphCode assistant that answers with repository context across many repos.
Plan-first coding agent that keeps the plan reviewable.
Larger changes where the plan is the artefact you want to review
Quick edits — the plan step is overhead
A terminal agent that separates planning from execution: it writes a plan you can read and change, then applies it in steps. The design encodes the main failure of autonomous coding — the agent implements something other than the intended change — by making the plan the first review surface.
Code assistant that answers with repository context across many repos.
Terminal coding agent that runs in your terminal with any model.
A fast native editor with an agent panel and multiplayer editing built in.
3 alternatives overlap with this one. Compare them →
Gives the model a scratchpad for structured, revisable reasoning: numbered thoughts that can branch, revise, and conclude. It does not make a weak model strong, but …
Pulls LangSmith traces and runs: inputs, outputs, latency, and errors for a project. It turns 'the agent is flaky' into a specific failing step, which is the only wa…
Serves version-specific documentation for thousands of libraries, so an agent stops writing code against an API that changed two releases ago. The practical fix for …
Turn an incident list into a decision about what to fix next.
Tree-of-thought exploration with explicit pruning before any code is written.
Derive contract tests from an API description, not from the implementation.