Review economics
assafelovic/gpt-researcher
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took only 0.8× the reviews submitted of the rest.
≥11%
Attributed
a floor
16
Attributed PRs
84
Other PRs
100
Read
Attributed — the latest 5
#1913 docs(skill): fix drift in .claude reference docs (retrievers, multi-agents, api)
0 reviews · 0h to merge
#1912 chore(multi_agents): nest AG2 variant under multi_agents/ag2
0 reviews · 0h to merge
#1857 Add Deep Agents example: GPT Researcher as the research engine in a LangChain deep agent
0 reviews · 8.5d to merge
#1861 Fix silently dropped token limits, real usage-based cost tracking, and research pipeline robustness
0 reviews · 7.9d to merge
#1820 security: sanitize untrusted content, add SECURITY.md, pin brotli
0 reviews · 2.7d to merge
The rest — the latest 5
#1891 feat: add Nebius Token Factory as LLM and embedding provider
1 reviews · 2.1d to merge
#1911 Reconcile master→main: GetXAPI retriever, Claude 4.x temp fix, MiniMax M3, curate_sources fixes
0 reviews · 1h to merge
#1910 Core/misc hardening: 11 fixes (costs/query/llm/agent/mcp/config) (supersedes #1822…#1902)
0 reviews · 3h to merge
#1909 Multi-agent robustness: bound revision loops + exact sentinels (supersedes #1883/#1885/#1886)
0 reviews · 3h to merge
#1908 Scraper robustness: 6 fixes (title/PDF-detection/temp-file/dimensions) (supersedes #1824…#1842)
0 reviews · 3h to merge
How this was measured
11% of merged commits carry agent attribution — a floor, not the share; tools that only complete code inline leave no commit trail, so the unattributed side includes AI-assisted work; reads 100 of 571 merged PRs — the rest have not been analyzed yet.
Detected: Claude Code, Cursor agent, GitHub Copilot coding agent, Google Jules.
“Attributed” means a commit carried an agent’s signature — a co-author trailer, an agent commit identity, or an agent bot account. Tools that only complete code inline leave no such mark, so the other column is “rest”, not “human-written”. Full method and its limits
The badge reads this repo’s current report, so it follows the number.
Tell me when this moves
We re-read assafelovic/gpt-researcher weekly and email only when the number changes materially.
Read your own repos
This one is public. For a private repo, run the same read locally through your own GitHub credentials — nothing is installed and nothing is sent to us.
npx @ambera/review-taxWant this continuously on assafelovic/gpt-researcher — each pull request paired to the task it came from, and the work graded from its review loop rather than its diff size? Claim this repo in Forge
Browse every repo people have read · Read a different repository