code-generation-agent

Here are 7 public repositories matching this topic...

dcondrey / misterdev

Autonomous LLM build orchestrator: plans a goal into tasks, edits code with anchored SEARCH/REPLACE, and verifies every change through build/test/lint/typecheck gates before reporting done. Runs as a CLI or MCP server.

tree-sitter mcp claude autonomous-agent llm llmops anthropic openrouter llm-agents llm-orchestration agentic-ai-development model-context-protocol mcp-servers coding-agent agentic-coding swe-bench ai-coding-assistants autonomous-coding-agent code-generation-agent

Updated Oct 22, 2026
Python

Nezarabdluah / My-Programming-Workflow

Star

A governance and operating system for AI coding agents — controlling execution, context, verification, evidence, and project memory.

code-generation ai-agents code-generation-techniques ai-governance coding-agents ai-coding developer-tools-ai-agent ai-governance-framework code-generation-ai-agents code-generation-agent code-generation-ai-workflow coding-agentsagentic-ai

Updated Sep 19, 2026
Python

SHalimoosavi / SYJ-AI

Star

Open-source, local-first autonomous AI software engineering agent — runs offline via Ollama, mobile-ready, from Android to Linux/Windows/macOS.

python open-source development devtools termux rcp autonomous-agents cli-tool ai-agent llm local-ai ollama qwen deepseek offline-ai qwen-coder ai-coding-assistant software-engineering-agent code-generation-agent

Updated Jul 18, 2026
Python

sylenthai / dream-rsi

Star

Research-grade platform for replay-based recursive policy improvement, autonomous codebase self-evolution, and safe sandboxed execution.

python ai python3 software code-generation autonomous-agents rsi ai-agents docker-sandbox fastapi llm llm-agents recursive-self-improvement rsi-ai self-evolution autonomous-agents- autonomous-agents-system code-generation-agent autonomous-agents-llm

Updated Sep 23, 2026
Python

alexandre0sheva / idea-to-mvp

Star

Turn a rough idea into a built, tested MVP: a multi-LLM panel debates it, you approve every gate, then sandboxed Claude agents build and verify it in parallel. Honest verdicts: parsed test reports, held-out acceptance tests, test-integrity guard. LangGraph, Gradio UI, CLI, MCP server, benchmark.