Show HN: Tanchi – Open-source AI prospecting agent that only automates email
Autonomous B2B prospecting engine — open source, self-hostable. The AI sources, researches, writes and follows up every night. The system learns from what actually converts, not from what looks nice.
- ▪Autonomous B2B prospecting engine — open source, self-hostable.
- ▪The AI sources, researches, writes and follows up every night.
- ▪The system learns from what actually converts, not from what looks nice.
Hacker News (AI / LLM) files mainly under ai. We currently carry 4,645 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/tanchihq/tanchi |
| Publication time | Wed, 12 Aug 2026 16:28:30 +0000 |
| Retrieval time | 2026-08-12T16:36:31.691Z |
| Last seen | 2026-08-12T16:36:31.691Z |
| 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 | ZTjLT_p08XdZ · 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
Your prospecting runs at night. You approve in the morning. Autonomous B2B prospecting engine — open source, self-hostable. The AI sources, researches, writes and follows up every night. You stay in control of what gets sent. The system learns from what actually converts, not from what looks nice. Tanchi takes the opposite stance to most AI prospecting tools: Email-first. The only channel that is genuinely safe to automate. Everything else is assisted (the AI drafts, a human sends). Verified intelligence. Every fact in a prospect dossier is sourced from the prospect's own website or LinkedIn. Never invented, never a filled-in gap. Qualitative learning first. We distill, in plain language, what converts per ICP before any statistics. Interpretable, correctable, effective from month one.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.