Show HN: Ctxdiff – Git diff for your LLM agent's context window
ctxdiff Find the character that's breaking your agent's prompt cache on every turn — and the tool schemas you pay for on every call but never invoke. git diff for your agent's context window: see exactly what your LLM saw, turn by turn, block by block. Pick your language: 🐍 Python · 🟨 JavaScript / TypeScript — same .ctrace format, same CLI, cross-compatible. ctxdiff is a local-first debugger for the context window of LLM agents. Vertex AI), or Bedrock client in one line — or hand a callback handler to LangChain/LangGraph — run your agent, and every call's context is recorded — as content-hashed, deduplicated blocks — into a single-file SQLite trace you can inspect, diff, and share.
- ▪ctxdiff Find the character that's breaking your agent's prompt cache on every turn — and the tool schemas you pay for on every call but never invoke. git diff for your agent's context window: see exactly what your LLM saw, turn by turn, blo
- ▪Pick your language: 🐍 Python · 🟨 JavaScript / TypeScript — same .ctrace format, same CLI, cross-compatible. ctxdiff is a local-first debugger for the context window of LLM agents.
- ▪Vertex AI), or Bedrock client in one line — or hand a callback handler to LangChain/LangGraph — run your agent, and every call's context is recorded — as content-hashed, deduplicated blocks — into a single-file SQLite trace you can inspect,
Hacker News (AI / LLM) files mainly under ai. We currently carry 2,444 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | GitHub |
| Canonical URL | https://github.com/salmanzafar949/ctxdiff |
| Publication time | Mon, 27 Jul 2026 14:14:05 +0000 |
| Retrieval time | 2026-07-27T14:26:23.336Z |
| Last seen | 2026-07-27T14:26:31.874Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | nPrDxZejiKk0 · 1 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
ctxdiff Find the character that's breaking your agent's prompt cache on every turn — and the tool schemas you pay for on every call but never invoke. git diff for your agent's context window: see exactly what your LLM saw, turn by turn, block by block. Pick your language: 🐍 Python · 🟨 JavaScript / TypeScript — same .ctrace format, same CLI, cross-compatible. ctxdiff is a local-first debugger for the context window of LLM agents. Wrap your OpenAI, Anthropic, Gemini (incl. Vertex AI), or Bedrock client in one line — or hand a callback handler to LangChain/LangGraph — run your agent, and every call's context is recorded — as content-hashed, deduplicated blocks — into a single-file SQLite trace you can inspect, diff, and share. Nothing leaves your machine.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.