Skip to content

Entry

Atomic Agent

Appears in 5 awesome lists

Orchestrator and worker split inside an MIT local-first agent: the orchestrator only plans, writes a brief per part and reviews (write, edit and shell calls are refused for the whole turn), workers run as short-lived sessions that write files to disk, and either seat can be a local llama.cpp model…

Open github.comatomicbot-ai/atomic-agent

Found in these lists

Awesome Agent Orchestrators

Section: Multi-Agent Swarms · Local-first desktop and terminal agent whose Fusion mode has one model plan, brief and review while a pool of worker sessions builds the parts in parallel, with a spend cap per turn and optional git worktree per worker. Local llama.cpp models, OpenRouter and other OpenAI-compatible providers, on…

FreshScore 86

Awesome AI Coding Tools

Section: Coding Agents · Local-first coding agent that runs open-weight models entirely on your machine via a llama.cpp fork. 56 built-in tools (browser, filesystem, git, memory, vision), MCP support, and a five-layer memory system. No account or API key required.

FreshScore 82

Awesome Harness Engineering

Section: Task Runners & Orchestration · Orchestrator and worker split inside an MIT local-first agent: the orchestrator only plans, writes a brief per part and reviews (write, edit and shell calls are refused for the whole turn), workers run as short-lived sessions that write files to disk, and either seat can be a local llama.cpp model…

FreshScore 93

Awesome LLM Resources

Section: 代码 Coding

FreshScore 91

Awesome LLMOps

Section: Code AI · Local-first CLI and TUI coding agent that runs open-weight models entirely on your machine through a llama.cpp fork. No account or API key required. 56 built-in tools (browser, filesystem, git, memory, vision), MCP support, five-layer local memory, macOS/Linux/Windows.

FreshScore 91

LiteLLM

Unified proxy and SDK that routes to 100+ LLM providers behind a single OpenAI-compatible interface, with a Router handling retry/fallback across deployments, per-project cost and rate-limit tracking, and OTEL callback integrations. The right infrastructure layer when your harness needs provider…

In 16 listsDetails

PydanticAI

June 2026 harness-first redesign built around the Capability primitive: a single composable unit bundling instructions, tools, lifecycle hooks, and model settings. The split between a small stable core and a fast-moving pydantic-ai-harness lets capabilities graduate as they prove essential, while…

In 13 listsDetails

AutoGen

Microsoft's multi-agent conversation framework with a complete AgentChat layer covering agent loop, tool integration, termination conditions, and human-in-the-loop. The most comprehensive open-source reference for large-scale multi-agent harness design.

In 14 listsDetails

Mastra

TypeScript-native agent framework (from the Gatsby team) with 22K+ stars and 300K+ weekly npm downloads. Connects to 40+ providers through one standard interface, with built-in workflows, RAG pipelines, and agent orchestration. The @mastra/deployer handles serverless deployment, and the eval…

In 12 listsDetails

CrewAI

Dual-layer harness orchestration: Crew handles autonomous agent delegation, Flow provides event-driven deterministic control (branching + shared Pydantic state). The clearest open-source example of mixing autonomous and scripted execution in the same harness.

In 10 listsDetails

OpenAI Agents SDK

Lightweight multi-agent framework built around handoffs and guardrails; the production successor to Swarm. Complements LangGraph for harnesses where delegation patterns are simpler than full graph orchestration.

In 9 listsDetails

LangGraph

LangGraph is a Python library facilitating the construction of stateful, multi-actor applications with LLMs, enabling cyclic coordination across multiple computation steps, particularly suited for agent-like behaviors, while also providing streaming support, and various guides and examples for…

In 8 listsDetails

PraisonAI

Praison AI is a low-code, centralized framework leveraging AutoGen and CrewAI to simplify creating and orchestrating multi-agent systems for LLM applications, emphasizing customization and ease of human-agent interaction github | demo | website

In 9 listsDetails