egma-ai/egma
the first open-source platform for simulation testing, monitoring and self-improving voice agents
About the project
Open-source platform for simulation testing and production monitoring of voice agents. Supports LiveKit (JS/TS) and Retell, runs regression suites and checks behavior with graders.
Useful for
- Build regression suites with simulated voice conversations for a voice agent
- Review real conversations and tool calls to investigate production failures
- Self-host Egma with your own API keys for model providers
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- The repository is 43 days old and already has 121 stars.
- Hacker News: “Show HN: Open-source simulation testing infra for voice agents” — 16 points, 3 days ago.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 121
- Stars in a day
- 0
- Forks
- 4
- Issues and pull requests
- 356
- Watchers
- 0
- Language
- TypeScript
- Latest release
- cli-v0.3.3 · September 4, 2026
- Created
- August 1, 2026
- Last push
- September 12, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Hacker News discussions
- Show HN: Open-source simulation testing infra for voice agents16 points, September 10, 2026
Spotted in
- September 13, 2026Spotted on Hacker News
Similar projects
-
6.8
melgarafael/DeskcommCRM
Self-hosted CRM with native AI agents for selling over WhatsApp: agents reply, qualify leads and close sales while your data stays on your server. An open alternative to Kommo, Octadesk and Intercom.
-
6.2
kruzovic7/ai-data-extractor
Python tool that extracts local chat histories from AI coding assistants (Claude Code, Cursor, Windsurf, Aider, Cline/Roo Code and more) into a single normalized JSONL format.
-
6.2
ayghri/i-have-adhd
A skill for a coding agent (Claude Code) that makes it lead with the answer and numbered steps, without preamble or filler. Helps you get concrete actions instead of long-winded reasoning.
-
6.1
tech-leads-club/agent-skills
A registry of validated skills (instruction plugins) for AI coding agents: extends Claude Code, Cursor, Copilot and others with secure, tested capabilities.
-
6.1
jordan-gibbs/hyperresearch
A deep research harness for Claude Code: turns one prompt into a report with verified citations and a persistent source vault. Every source lands in a searchable store reused by later sessions.
-
6.0
NVlabs/SoL-Pi
An extension for Pi that cuts token usage and redundant turns of coding agents via four mechanisms: action fusion, observation packing, log reduction, and context compaction.