Hi Rasa team,
Your project RasaHQ/rasa is impressive — 21295 stars says it all. One thing
I noticed: agents built on it forget everything between sessions, and
sending ALL memory to the model on every request costs a fortune.
ViBo solves this — memory for AI agents:
- 🧠 Encrypted L1/L2/L3: secrets (API keys) NEVER reach the LLM
- 🌐 Web search savings: articles compressed 47,443 → 186 tokens (99.6%)
- 💬 Thread memory: conversations -72%, details restored on demand
- Measured: 118 facts → 263 tokens instead of 13,775 (97.5% fewer)
Integrates via Python API or MCP (any agent, any framework).
Works with your stack in minutes.
Model: $5/month, 2-day free trial (key built-in).
Site: https://wwwvibo.com · Docs: https://github.com/vnbochkarev-netizen/ViBo-memory
Happy to discuss integration or partnership (30% recurring for
referrals). Honest limits: code gen doesn't save — we say so openly.
Best,
ViBo team
Hi Rasa team,
Your project RasaHQ/rasa is impressive — 21295 stars says it all. One thing
I noticed: agents built on it forget everything between sessions, and
sending ALL memory to the model on every request costs a fortune.
ViBo solves this — memory for AI agents:
Integrates via Python API or MCP (any agent, any framework).
Works with your stack in minutes.
Model: $5/month, 2-day free trial (key built-in).
Site: https://wwwvibo.com · Docs: https://github.com/vnbochkarev-netizen/ViBo-memory
Happy to discuss integration or partnership (30% recurring for
referrals). Honest limits: code gen doesn't save — we say so openly.
Best,
ViBo team