Skip to content

Nodenester/AutonomousAgent

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

AutonomousAgent

An autonomous AI agent framework built in April 2024. Early experiment in building a self-directing agent loop that plans, decomposes tasks, remembers context, and calls tools — all running against local open-source LLMs.

What it does

The agent takes a goal from the user and autonomously works toward it through a continuous loop:

  1. Plan — generates a strategic plan for the goal
  2. Decompose — breaks the plan into a concrete task list
  3. Execute — iterates through tasks, calling tools and updating state each step
  4. Remember — retrieves relevant past context via vector-based memory (cosine similarity RAG)
  5. Complete — signals when the goal is achieved

Tool calls are parsed from XML (<tool_call>) in the LLM output — no function-calling API needed, works with any completion endpoint.

Components

Component What it does
Agent Holds agent state (goal, plan, task list, dialog history, vector DB) and runs the main loop
Executor Calls the LLM, parses tool calls from the response, dispatches to tool handlers
PromptGenerator Builds ChatML-format prompts with system instructions, tool definitions, task state, memory, and dialog history
RetriveMemory Vector RAG — embeds the current query, finds relevant past entries via cosine similarity
BaseFunctions Tool implementations: SetPlan, TaskListCreationOrUpdate, IsGoalAchieved
LlamaInfer HTTP client for a local llama.cpp-compatible inference server (text generation + embeddings)
VectorService Persistence layer for the vector database (JSON on disk)
AgentService Persistence layer for agent state (JSON on disk)

Tech

  • C# / .NET 8
  • Local LLM inference via a llama.cpp-compatible HTTP server on localhost:5037
  • Built for open-source models (Qwen, Mistral, etc.) using ChatML prompt format
  • No external API dependencies — everything runs locally

Context

This was an early experiment from April 2024 — two commits, proof of concept. The ideas are straightforward (agent loop, tool use, vector memory), but it was a useful exercise that shows the trajectory from "what if I just let an LLM loop on itself" to more structured agent systems.

License

MIT — see LICENSE.

About

Autonomous AI agent framework (April 2024). Self-directing agent loop with planning, task decomposition, vector RAG memory, and tool use — built for local LLMs. C#, .NET 8.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages