October 27, 2026
Does your model know the library version you're using?
We tested six coding models on six libraries. Providing version-specific definitions through GitHits raised correct API calls from 60–68% to about 94%.
Topic
27 posts in this topic.
October 27, 2026
We tested six coding models on six libraries. Providing version-specific definitions through GitHits raised correct API calls from 60–68% to about 94%.
October 22, 2026
A change in one project can break another. We tested how agents handle 42 tasks with source access through GitHits, local clones, or neither.
October 22, 2026
A library upgrade can change your application without changing its code. We tested agents that compare default settings in the old and new releases.

October 21, 2026
We used GitHits to inspect how SPACE pauses agent environments, copies their work, and adds API credentials outside the sandbox.
October 15, 2026
An error message is a starting point. We tested an agent that searches the exact library version to find the file and function that produced it.
October 13, 2026
Before upgrading a dependency, check which known security issues it fixes or adds. We tested a small agent that gathers the data through GitHits.

September 21, 2026
Software factories and agents still need to read code. GitHits provides infrastructure to discover open-source code and verify how it behaves.

August 27, 2026
How coding agents inspect external open-source dependencies across the software development lifecycle (SDLC).

August 24, 2026
Coding agents should inspect source code directly, use deterministic search for retrieval, and reserve model reasoning for understanding and decisions.

August 17, 2026
We ran the same model and the same prompt twice to build a Three.js game — one agent with GitHits, one without. Here is how far each got.
July 21, 2026
We used GitHits to explore the Postgres 19 release and surface what changed. Six features came back. A coding agent without GitHits could not reach any of them.

July 20, 2026
How Agent Runner went from a 23-minute prototype to a finished game built with coding agents, source context, generated concepts, and hand-made art.

July 7, 2026
A source-backed comparison of Apple container and Docker Desktop on macOS, using GitHits to trace every architecture claim to docs and code.

June 30, 2026
Compare GitHits and Context7 for AI coding agents: docs, implementation examples, source navigation, package metadata, MCP, and CLI workflows.

June 22, 2026
Install the GitHits onboarding skill so your agent can create your account, configure supported tools, and guide setup from one prompt.

June 16, 2026
A look under the hood of GitHits, what a real open-source index requires, and why search-and-rerank depends on its source.

June 15, 2026
How Codex fixed an offline checkout mutation that stopped working after reload.

June 14, 2026
How Codex fixed Pydantic AI tools that ignored per-run tenant data.

June 10, 2026
A new code navigation skill gives your agent search, file listing, read, and grep across a codebase, so its answers come from the actual code.

June 10, 2026
Use GitHits in the research phase to compare coding agents by their real behavior, before you clone a repo or write code.

June 10, 2026
Run one init command to detect your installed agents, configure them to use GitHits, and sign in, at the user or project level.

June 10, 2026
A new package skill gives your agent license, dependency, vulnerability, changelog, and upgrade-review data before you add a dependency.

June 3, 2026
How Codex fixed a DuckDB v1.3.2 table function migration with version-specific source from GitHits.

June 3, 2026
How Codex migrated dynamic SQL to SQLx 0.9 without turning user input into query text.

May 7, 2026
GitHits CLI is here. Install in one command and give agents 14 tools for code search, package inspection, documentation, and grounded open-source examples.

May 5, 2026
Nathan Burg on source-grounded context for coding agents, and why real data matters when building AI workflows developers can actually trust.

April 23, 2026
Olli-Pekka Heinisuo on how open-source code becomes useful context for coding agents, from generic answers to grounded examples from real repos.