Harness Engineering — Technology Landscape

SDD — Spec-Driven Development
OpenSpec
Fission-AI/OpenSpec
Spec-driven development for AI coding assistants
★ 67.6k
spec-kit
github/spec-kit
Toolkit to get started with Spec-Driven Development
★ 134.0k
BMAD
bmad-code-org/bmad-method
Breakthrough Method for Agile AI Driven Development
★ 52.8k
Spec Kitty
spec-kitty/spec-kitty
Spec Kitty is an open-source CLI for turning product intent into a repo-native AI coding workflow:
★ 1.6k
Specula
specula-org/Specula
Specula: An agentic tool for finding deep bugs in system code using TLA+. It uses coding agents to write TLA+ specs of the target system.
★ 447
GSD Core
open-gsd/gsd-core
Context-engineering and spec-driven development framework that drives AI coding agents
★ 9.2k
Coding Assistants — Coding assistants usable from a terminal
General Purpose
pi.dev
earendil-works/pi
Minimal agent harness — adapt to your workflow, not vice versa
★ 103.0k
OpenCode
anomalyco/opencode
OpenCode is an open source agent that helps you write code in your terminal, IDE, or desktop.
★ 205.8k
NanoCoder
Nano-Collective/nanocoder
An open coding agent for your terminal, built by a community collective rather than a company. Bring your own model, keep your code on your machine, and owe nothing to anyone.
★ 2.5k
Qwen Code
qwenLM/qwen-code
An open-source AI agent for the terminal, optimized for Qwen series models
★ 27.7k
DeepSeek Harness
deepseek-ai/deepseek-harness
Open-source agent harness developed by DeepSeek AI
★ 215.9k
jcode
1jehuang/jcode
The most RAM efficient harness
★ 19.3k
Local-First
Codehamr
codehamr/codehamr
A minimal, local-first coding agent.
★ 216
Atomic Agent
AtomicBot-ai/atomic-agent
A local-first AI agent that runs on your machine, with local or cloud models.
★ 2.5k
SDLC Templates or Template Management — Holding agentic configurations, skills, etc.
OpenViking
volcengine/OpenViking
Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
★ 36.0k
Mimir
FeatureFactory-io/mimir
Mimir is a foundation for self-evolving methodologies for well-defined tasks
★ 13
ArcKit
tractorjuice/arc-kit
ArcKit is an enterprise Architecture governance harness that wraps your AI coding assistant
★ 2.2k
Hivemind
hivementality-ai/hivemind
Self-hosted multi-agent AI team platform. 40+ built-in tools, 150+ agent templates.
★ 75
OpenHands
OpenHands/OpenHands
The self-hosted developer control center for coding agents and automations.
★ 86.8k
Orchestration
Symphony
openai/symphony
Isolated autonomous implementation runs for teams
★ 27.1k
Conductor
microsoft/conductor
Multi-agent workflows with GitHub Copilot SDK
★ 424
OpenSquilla
opensquilla/opensquilla
Token-efficient AI agent with higher intelligence density
★ 7.0k
Fabro
fabro-sh/fabro
Version-controlled workflow graphs orchestrating AI agents, commands, and human gates
★ 1.6k
smolagents
huggingface/smolagents
Barebones library for agents that think in code
★ 29.2k
OpenHive
aden-hive/hive
Multi-agent harness for production AI workloads
★ 11.0k
bernstein
sipyourdrink-ltd/bernstein
Audit-grade multi-agent orchestration, HMAC-chained audit log
★ 1.1k
T3 Code
pingdotgg/t3code
T3 Code is an agent harness control surface.
★ 22.1k
Scion
GoogleCloudPlatform/scion
Scion is a container-based orchestration platform for running multiple LLM deep agents concurren
★ 1.7k
AST and Code Parsers
CocoIndex Code
cocoindex-io/cocoindex
AST-based lightweight code search engine CLI; saves 70% tokens
★ 11.5k
CodeGraphContext
CodeGraphContext/CodeGraphContext
MCP server indexing local code into a graph database
★ 4.2k
ast-grep
ast-grep/ast-grep
CLI tool for code structural search, lint and rewriting in Rust
★ 15.8k
ripwire
redhat-et/ripwire
The ripgrep of AI context: a zero-dependency C++23 CLI + MCP server for coding agents.
★ 1.6k
Graphify
Graphify-Labs/graphify
Turn code and docs into queryable AI knowledge graphs
★ 115.9k
Understand Anything
Egonex-AI/Understand-Anything
Turn any codebase, knowledge base, or docs into an interactive knowledge graph you can explore, search, and ask questions about.
★ 81.8k
Sandboxes
NVIDIA OpenShell
docs.nvidia.com
Sandboxed agent runtime with hardware-enforced isolation and policy
forkd
deeplethe/forkd
fork() for AI agent microVMs; spawn 100 children in ~100ms
★ 2.8k
OpenSandbox
opensandbox-group/OpenSandbox
Secure, fast, extensible sandbox runtime for AI agents
★ 15.0k
Daytona
daytonaio/daytona
Elastic infrastructure for running AI-generated code; sub-90ms creation
★ 71.8k
E2B
e2b-dev/e2b
E2B provides isolated sandboxes that let agents safely execute code, process data, and run tools.
★ 13.7k
Working with Skills
Skill Reference
Agent Skills
agentskills.io
Standardized open format for extending AI agent capabilities via SKILL.md files
Skill Syntax Validation
skill-validator
agent-ecosystem/skill-validator
Validates skill content against the Agent Skill specification
★ 237
Skill Repositories
OSMT
wgu-opensource/osmt
OSMT is the Open Skills Management Tool
★ 66
SkillHub
iflytek/skillhub
Self-hosted, open-source agent skill registry for enterprises.
★ 5.1k
Skill Dependency Management
skills (Vercel Labs)
vercel-labs/skills
Open agent skills CLI; supports OpenCode, Claude Code, Codex, Cursor and 68+ more
★ 30.7k
Microsoft APM (Agent Package Manager
microsoft/apm
An open-source, community-driven dependency manager for AI agents.
★ 3.8k
Skill Security Scanners
DefenseClaw
cisco-ai-defense/defenseclaw
Security governance for agentic AI; scan capabilities, inspect traffic, audit evidence
★ 833
SkillSpector
nvidia/skillspector
Security scanner for AI agent skills; detects vulnerabilities before installation
★ 16.6k
Knowledge Base
LLM Wikis
OpenKnowledge
inkeep/open-knowledge
Beautiful, AI-native markdown IDE and LLM wiki
★ 4.1k
pi-llm-wiki
zosmaai/pi-llm-wiki
Self-maintaining, Obsidian-compatible knowledge base for pi
★ 562
Open Knowledge Format (OKF)
OKF Ecosystem
okf.md
Open Knowledge Format ecosystem; tools, spec and docs for AI agent knowledge bases
okflint
mattdav/okflint
Deterministic compliance linter for OKF bundles; profile-based rule enforcement
★ 6
okf CLI
superops-team/okf
CLI for git-based OKF knowledge bases; keeps bundles fresh via git hooks
★ 25
OpenWiki
langchain-ai/openwiki
OpenWiki is a CLI that writes and maintains agent documentation for your codebase in OKF compatible format.
★ 16.2k
Technology Specifics
Context7
upstash/context7
Up-to-date documentation for LLMs and AI code editors
★ 61.8k
LangChain docs MCP + skills
docs.langchain.com
Use LangChain Docs Programmatically with MCP and installed skills
NVIDIA Agent Skills
nvidia/skills
Official NVIDIA-verified skills catalog for CUDA-X, AI Blueprints and platform tools
★ 3.2k
DataHub Skills
datahub-project/datahub-skills
Agent skills for working with DataHub
★ 38
Token Control
rtk
rtk-ai/rtk
CLI proxy reduces LLM token consumption by 60-90% on common dev commands; single Rust binary
★ 79.4k
ponytail
dietrichgebert/ponytail
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
★ 131.7k
Headroom Desktop
gglucass/headroom-desktop
MacOS menu bar app cuts Claude Code and Codex token costs by ~50%
★ 539
Caveman
JuliusBrussee/caveman
An efficiency stack for AI agents - cuts 65% of tokens by talking like caveman
★ 104.3k
Observability
Langfuse
langfuse/langfuse
Open source AI observability platform; LLM evals, metrics, tracing, prompt management
★ 34.3k
Phoenix
Arize-ai/phoenix
AI observability and evaluation by Arize; traces, evals, datasets
★ 11.4k
Claude Code - OTEL
code.claude.com
How to enable and configure OpenTelemetry for Claude Code.
SigNoz - Coding agent observability
signoz.io
ClaudeCode observability with SigNoz and OpenTelemetry
agentops
AgentOps-AI/agentops
Python SDK for AI agent monitoring, LLM cost tracking, benchmarking
★ 5.8k