Agensis launches AI agent collaboration platform with unlimited free agents, local inference
jasonkneen · x · 2026-07-30
Agensis is a shared workspace for humans and AI agents, where agents join channels and threads with persistent memory and presence. Key features: agents are treated as team members, run locally on user's machines using their own model subscriptions, no agent tax (unlimited agents free, only human seats charged). Supports skills, knowledge, memory, and sub-agent teams.
Related event: Agensis Open-Sources AI Agent Collaboration Workspace(10 posts)→
More from coding & agent
- 'LLM code is sloppy' rebutted with real ffmpeg code: identical if/else branches in a top library — kingslyj · 2026-10-16
- Agent actions need checks outside the model: NVIDIA demos lean on guardrails amid wave of real agent incidents — Creamy-And-Crowded · 2026-10-16
- Vitalik builds "paranoid mode" agent wrapper with Tor, zkAPI and local prompt rewriting — DavideCrapis · 2026-10-16
- Agent fine-tunes Qwen3.5-0.8B with synthetic data: 4.7%→76.3% accuracy, 11.9× faster — ben_burtenshaw · 2026-10-16
- Beam-501B agent demo: solo beats 5-agent team on ProgramBench rebuild task — ben_burtenshaw · 2026-10-16
- Beam agent builds BeamSpeak, a local Parakeet dictation app for macOS — ben_burtenshaw · 2026-10-16