#autonomous-agents

Production-ready AI Business OS — 46 autonomous AI Employees, Graph RAG (Neo4j), multi-channel, BYOK across 17 LLM providers plus custom/local endpoints (Ollama), automatic fallback. 8 libs (Python+Java). Self-hosted, MIT licensed, guardrailed autonomy for regulated industries.

Autonomous AI agents you deploy in 30 seconds across any channel. Zero-config CLI, 37 channel adapters, HEXACO personality and cognitive memory powered by AgentOS, five-tier prompt-injection defense.

TypeScript harness for building personal AI agents with durable memory — agents that live across your channels (CLI, Teams, iMessage, mail, voice), use real tools, and stay coherent across turns. The runtime behind @ouro.bot.

An agentic software factory that closes the loop

security

Soma makes AI agents trustworthy by providing observably traceable governance, evidence-based rule selection W/ JIT, AST analysis tools, TTC Verifiers, and adaptive rule lifecycle management.

A scientific-method runtime for AI agents: hypotheses, experiments, evidence, provenance, reproducibility, and auditable conclusions.

turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then runs tree search with parallel subagents.

The autonomous delivery engine for Baton: a vendor-neutral team of agents that plans, builds, verifies, and merges software.

Provider-neutral, self-hosted reference runtime for autonomous agents (Toll Bench harness).

🔁 Finishes your entire backlog while you sleep. The AI orchestrator that DOES the work end-to-end on ANY LLM — discover → implement → verify → merge → 24/7 — behind safety gates, at up to 90% fewer tokens. 48 extension points. Not a chatbot. A worker.

🤖 Autonomous Multi-Agent AI Workspace in your terminal. Codes, researches, and executes real tasks with 40+ tools and 280+ skills And Some Captcha Resolver With Only Vision Mode Any Captcha And Opening A Browser And Full Control Of It

Fully autonomous AI dev agent in pure Go built on empirical research. Get real work done on consumer hardware, even with tiny context windows.

Build, test, and deploy intelligent AI agents the Laravel way

Autonomous agent ecosystem — CLI tools that provision, scaffold, and maintain Claude Code agent ecosystems

SnapDB — Extremely lightweight lightning-fast in-memory database for Python. Zero-copy reads, single-file, pure Python.

Sovereign P2P networking tool. Post-quantum encrypted connections, identity, file transfer, and relay infrastructure. No cloud, no accounts, no trust assumptions.

Deterministic, evidence-based build harness for autonomous coding agents — FSM sprint gates, execution-evidence verification, and adversarial critics. Proof, not opinion.