Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
45 changes: 0 additions & 45 deletions .github/workflows/claude-code-review.yml

This file was deleted.

35 changes: 25 additions & 10 deletions .github/workflows/claude.yml
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,8 @@ on:
types: [opened, assigned]
pull_request_review:
types: [submitted]
pull_request:
types: [opened, synchronize, ready_for_review, reopened]

jobs:
claude:
Expand All @@ -23,7 +25,7 @@ jobs:
pull-requests: write
issues: write
id-token: write
actions: read # Required for Claude to read CI results on PRs
actions: read
steps:
- name: Checkout repository
uses: actions/checkout@v4
Expand All @@ -35,16 +37,29 @@ jobs:
uses: anthropics/claude-code-action@v1
with:
anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}

# This is an optional setting that allows Claude to read CI results on PRs
additional_permissions: |
actions: read

# Optional: Give a custom prompt to Claude. If this is not specified, Claude will perform the instructions specified in the comment that tagged it.
# prompt: 'Update the pull request description to include a summary of changes.'

# Optional: Add claude_args to customize behavior and configuration
# See https://github.com/anthropics/claude-code-action/blob/main/docs/usage.md
# or https://code.claude.com/docs/en/cli-reference for available options
# claude_args: '--allowed-tools Bash(gh pr:*)'
review:
if: github.event_name == 'pull_request'
runs-on: ubuntu-latest
permissions:
contents: read
pull-requests: write
issues: write
id-token: write
steps:
- name: Checkout repository
uses: actions/checkout@v4
with:
fetch-depth: 1

- name: Run Claude Code Review
id: claude-review
uses: anthropics/claude-code-action@v1
with:
anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
plugin_marketplaces: 'https://github.com/anthropics/claude-code.git'
plugins: 'code-review@claude-code-plugins'
prompt: '/code-review:code-review ${{ github.repository }}/pull/${{ github.event.pull_request.number }}'
allowed_tools: 'Bash(gh pr *),Bash(gh api *),Bash(git diff *),Bash(git log *),Read,Glob,Grep'
10 changes: 5 additions & 5 deletions FOUNDATION.md
Original file line number Diff line number Diff line change
Expand Up @@ -98,15 +98,15 @@ This matters because codegraph runs inside AI agents that have broad tool access

### 8. Honest about what we're not

**We are not a graph database. We are not a RAG system. We are not an AI agent.**
**We are not an application. We are not a coding tool. We are not an AI agent.**

We use SQLite, not Neo4j/Memgraph/KuzuDB. Our queries are hand-written SQL, not Cypher. This is intentional — it keeps us at zero infrastructure.
We are a code intelligence engine — a library that parses, indexes, and queries structural relationships. We don't have a GUI, we don't open in a browser, and we don't present dashboards. Applications are built *on top* of codegraph, not inside it.

We offer semantic search via optional embeddings, but we are not a RAG pipeline. We don't generate code, answer questions, or translate natural language to queries.
We offer semantic search via optional embeddings, but we are not a coding assistant. We don't generate code, suggest fixes, refactor, or translate natural language to code. Tools that do those things can use our graph as their foundation.

We expose tools to AI agents via MCP, but we are not an agent ourselves. We don't make decisions, run multi-step workflows, or modify code.
We expose tools to AI agents via MCP, but we are not an agent ourselves. We don't make decisions, run multi-step workflows, or modify code. We answer structural questions so that agents can make better decisions.

Staying in our lane means we can be embedded inside tools that do those things — without competing with them or duplicating their responsibilities.
Staying in our lane means we can be embedded inside IDEs, AI agents, CI pipelines, and developer platforms — without competing with them or duplicating their responsibilities.

---

Expand Down
Loading