Open Source AI Harness Profiler – discover where tf your tokens are going
Token Profiler A transparent proxy for the Anthropic and OpenAI APIs that records token usage and shows it in a dashboard. Point your client at it, keep working as normal, and see per-request tokens, reconstructed sessions, tool-level attribution, and estimated cost. Built on Cloudflare Workers, D1, Hono, and React.
- ▪Token Profiler A transparent proxy for the Anthropic and OpenAI APIs that records token usage and shows it in a dashboard.
- ▪Point your client at it, keep working as normal, and see per-request tokens, reconstructed sessions, tool-level attribution, and estimated cost.
- ▪Built on Cloudflare Workers, D1, Hono, and React.
Hacker News (AI / LLM) files mainly under ai. We currently carry 3,263 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
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/TryRekon/Rekon |
| Publication time | Tue, 21 Jul 2026 21:17:28 +0000 |
| Retrieval time | 2026-07-21T23:06:08.221Z |
| Last seen | 2026-07-21T23:06:08.221Z |
| 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 | DXhEk20kS8u3 |
| 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
Token Profiler A transparent proxy for the Anthropic and OpenAI APIs that records token usage and shows it in a dashboard. Point your client at it, keep working as normal, and see per-request tokens, reconstructed sessions, tool-level attribution, and estimated cost. Built on Cloudflare Workers, D1, Hono, and React. A hosted instance runs at tryrekon.com. Features Zero added latency — responses stream straight through; recording happens off the critical path. Keys never stored — auth headers are forwarded, never held, so usage is always spent on the caller's own key or subscription. Session trees — the chat APIs are stateless, so the proxy rebuilds each conversation from client signals, forks and all. Tool-level attribution — see which tools actually burn the tokens.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.