hermes-research-agent

The self-improving AI agent built by Nous Research. It's the only agent with a built-in learning loop — it creates skills from experience, improves them during use, nudges itself to persist knowledge, searches its own past conversations, and builds a deepening model of who you are across sessions. Run it on a $5 VPS, a GPU cluster, or serverless infrastructure that costs nearly nothing when idle. It's not tied to your laptop — talk to it from Telegram while it works on a cloud VM.

Use any model you want — Nous Portal, OpenRouter (200+ models), z.ai/GLM, Kimi/Moonshot, MiniMax, OpenAI, or your own endpoint. Switch with hermes model — no code changes, no lock-in.

A real terminal interface Full TUI with multiline editing, slash-command autocomplete, conversation history, interrupt-and-redirect, and streaming tool output. Lives where you do Telegram, Discord, Slack, WhatsApp, Signal, and CLI — all from a single gateway process. Voice memo transcription, cross-platform conversation continuity. A closed learning loop Agent-curated memory with periodic nudges. Autonomous skill creation after complex tasks. Skills self-improve during use. FTS5 session search with LLM summarization for cross-session recall. Honcho dialectic user modeling. Compatible with the agentskills.io open standard. Scheduled automations Built-in cron scheduler with delivery to any platform. Daily reports, nightly backups, weekly audits — all in natural language, running unattended. Delegates and parallelizes Spawn isolated subagents for parallel workstreams. Write Python scripts that call tools via RPC, collapsing multi-step pipelines into zero-context-cost turns. Runs anywhere, not just your laptop Six terminal backends — local, Docker, SSH, Daytona, Singularity, and Modal. Daytona and Modal offer serverless persistence — your agent's environment hibernates when idle and wakes on demand, costing nearly nothing between sessions. Run it on a $5 VPS or a GPU cluster. Research-ready Batch trajectory generation, Atropos RL environments, trajectory compression for training the next generation of tool-calling models.

• zero-spec research starts: literature scan, idea generation, hypothesis creation, and first experiment planning
• partial-spec execution: fills in missing dataset, eval, and training details while preserving user constraints
• full-spec execution: runs the requested loop with approval gates only where configured
• durable long-running work: checkpoints loop state, monitors background runs, and writes unread inbox summaries on completion
• research management: literature triage, dataset quality scoring, experiment ranking, search pruning, failure recovery plans, and memo writing via research_manager
• 💬 Discord
• 📚 Skills Hub
• 🐛 Issues