>_Skillful
Need help with advanced AI agent engineering?Contact FirmAdapt

Search

@demigodmode/pi-web-agent

GitHub Actions

Pi package for reliable web access with explicit search, fetch, and headless boundaries.

AgentAI Tool
1 dir

agent-checkpoint-cas

Type-guided externalized state for LLM agent frameworks.

Agentai-agents
1 dir

opensmith

Local-first LLM pipeline tracer. No cloud. No setup.

Agentai-agents
1 dir

leafmesh

LeafMesh — YAML-native multi-agent orchestration platform

Agentai-agents
1 dir

FigureLabs

An AI tool for generating publication-ready scientific figures in vector format from text descriptions or sketches.

AgentServices
1 dir

tickerr-reporter

LiteLLM callback that reports LLM API failures to Tickerr — outage radar for AI agents.

Agentai-agents
1 dir

alex-code-review

Alex

Multi-agent code review system with LLM

Agentai-agents
1 dir

OpenHands-7B-Agent

SWE-Gym

AI model: SWE-Gym/OpenHands-7B-Agent

Agentai-model
1 dir

Qwen3-Space.Agent.Claude.Uncensored-4B.GGUF

WithinUsAI

AI model: WithinUsAI/Qwen3-Space.Agent.Claude.Uncensored-4B.GGUF

Agentai-model
1 dir

qwen3-4b-instruct-code-agent

Nanami14138

AI model: Nanami14138/qwen3-4b-instruct-code-agent

Agentai-model
1 dir

Agent-Hire-1B-Merged

Samridhi24

AI model: Samridhi24/Agent-Hire-1B-Merged

Agentai-model
1 dir

Kincode

LocalKinAI

AI coding assistant in Go. 9MB single binary, zero dependencies. MCP support, Soul files for custom AI personas. 10 built-in tools + sub-agents + web search + memory. The only Claude Code alternative with both MCP and Soul files.

...more
Agentdevtools
51 dir

Swarmauri Sdk

swarmauri

Modular Python SDK and monorepo for AI agents, LLM integrations, tools, parsers, embeddings, vector stores, and extensible application workflows.

...more
Agentai
1041 dir

Ephemera

steve-seungeui

Enterprise control plane for ephemeral AI agents via Firecracker MicroVMs

Agentcloud
31 dir

Trip Agent

akka-samples

LLM (Anthropic) with tools integration to find flights

Agentai
11 dir

PhysicianBench

HealthRex

The benchmark tasks and evaluation harness for "PhysicianBench: Evaluating LLM Agents in Real-World EHR Environments".

Agentuncategorised
431 dir

overcooked

Cooperative multi-agent environment based on Overcooked

Agentai-agents
1 dir

groundguard

LLM-agnostic deterministic assert layer for AI agent outputs

Agentai-agents
1 dir

agnostic-security

The firewall for AI coding agents — prevents secrets, PII, and credentials from leaking through Copilot, Claude Code, Cursor, and LangChain

...more
Agentai-agents
1 dir

llm-wf

Emmanuel Desmontils

Moteur de workflow LLM basé sur des graphes d'agents

Agentai-agents
1 dir