Build your own sales-call review tooling: 71 open Agent Skills that audit call transcripts and CRM exports against GTM rubrics, citing a quote for every finding. Local, no credentials.
-
Updated
Oct 19, 2026 - Python
Build your own sales-call review tooling: 71 open Agent Skills that audit call transcripts and CRM exports against GTM rubrics, citing a quote for every finding. Local, no credentials.
AI quality assurance for sales calls
Multi-tenant agentic AI SaaS that transforms multi-speaker audio into diarized transcripts, evidence-backed summaries, action items, and grounded Q&A.
Sales coaching runs on whoever happened to sit in on the call. This scores every call against the rubric instead: a verbatim quote behind every point given or withheld, and no score at all on calls that were never a pitch. Reviewing 15 calls a week by hand is 5 hours of someone's attention — this is one unattended run.
Open-source Revenue Intelligence — Multi-agent Gong alternative built with LangGraph, faster-whisper, PyAnnote, Presidio, and LLMs
Contact-center conversation intelligence: intent, sentiment, and escalation-risk scoring with an honest, reproducible evaluation dashboard
Clean ChatGPT conversation analysis tools without sensitive data
AI call intelligence for sales and customer-service teams: diarized transcripts, rubric scorecards where every point cites the audio, coaching, cross-call Q&A and follow-up tasks. Next.js + FastAPI.
Turn fundraising-meeting recordings into stable, comparable post-mortems — local-first transcription + a research-backed, stage-aware analysis framework. 把投资人/FA 会谈录音变成可纵向对比的复盘。
LLM-пайплайн анализа B2B-звонков с нехаллюцинирующими цитатами: модель ссылается на номер реплики, а не пересказывает текст — evidence-by-reference вместо fuzzy-match. Провайдер-агностично (DeepSeek/YandexGPT/GigaChat), PII-safe по архитектуре, живо протестировано против реального API.
Traceable conversation-intelligence pipeline with strict structured outputs, deterministic analytics, evidence-linked reports and CI.
Homayar — multi-tenant, Persian-first conversation intelligence platform for contact centers. One backend, four deployment modes (SaaS, connected on-prem, hybrid, air-gapped), governed AI routing.
A semantic interrupt controller: calibrated semantic channels sampled over a live conversation at 5Hz, firing only on a hysteresis-gated edge. The model decides when; your code decides what. TypeSafe Jev + Deepgram Flux, zero dependencies.
Open-source conversation intelligence and evidence-backed call scoring powered by LangGraph.
Collection of tools for analyzing ChatGPT and Claude conversation data with database queries, visualizations, and content analysis
Project-aware meeting conversation intelligence repo for analyzing and visualizing mood flow, signals, and turn-level patterns with FastAPI and React.
To associate your repository with the conversation-intelligence topic, visit your repo's landing page and select "manage topics."