Back to directory

Loki Agent

A self-hostable AI agent with a built-in learning loop that creates and improves its own skills from experience, searches its past conversations, and can run on a $5 VPS or be reached through Telegram, Discord, Slack or a terminal.

Loki Agent

Loki Agent runs against a user's choice of model provider, from OpenRouter or OpenAI to a self-hosted endpoint, switchable at any time with no code changes. Its closed learning loop creates new skills after complex tasks and improves them during later use, periodically nudges itself to persist knowledge, and searches its own past conversations with full-text search plus LLM summarization for cross-session recall.

It reaches users through a single gateway process across Telegram, Discord, Slack, WhatsApp, Signal and a full terminal UI, includes a built-in cron scheduler for unattended automations such as nightly backups, and can spawn isolated subagents for parallel workstreams. It runs on a small VPS, a GPU cluster, or serverless backends such as Modal or Daytona that hibernate the agent's environment when idle.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.