Search
@zyntrialabs/vintraa-agent-sdk
zyntrialabs
Framework-neutral TypeScript SDK for native Vintraa agents.
Habitus AI
munch2u-a11y
Habitus-AI is fundamentally new approach to AI Agent Memory Systems and Cognitive Harness. Dual-Cypher system runs along perpendicular graphs. Mutate edges in real time. Builds habits and dynamic personality traits. Can call tool reflectively, connect complex concepts to learned words, and send plain text outputs without needing an LLM
...moredagr-ai
Emre Barut
Workflow experimentation for agent orchestration. First release September 2026.
vintraa-agent
Zyntria Labs
Framework-neutral Python SDK for native Vintraa agents.
Thinking Machines: Inkling Small (batch)
thinkingmachines
Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...
...more@eternify-labs/seo-audit
parikrut
SEO & AEO auditor: score any domain or codebase, get an actionable report, and let an AI agent fix your code.
q-ai-governance
Jonathan Reiser
Quantum-Cognitive AI (Q-AI) Policy Agent & Real DAO Governance Decision Engine
pycarta-service-agent
Contextualize
Packaged Carta service agent binary and utilities for pycarta[service].
risenlab-agentlogs
RISEN Lab
Schema definitions and utilities for the AgentLogs dataset
ruhusa
Claire Muwanguzi
Continuous, least-privilege authorization for multi-agent AI systems.
neptune-code
Optccopa
A model harness like claudecode or codex built in python, supports Anthropic natively and a large amount of models via OpenRouter and Ollama
...moreJarvisNano
PascalAI2024
Voice-first J.A.R.V.I.S. desk companion for the Waveshare ESP32-S3 Touch AMOLED 1.75C — Gemini Live, reactive round UI, physical privacy, motion, OTA, and policy-gated MCP tools.
...moreOpencode Orchestrator Kit
NicoGenti
Cost-aware multi-agent orchestrator kit for OpenCode CLI — one routing agent, 14 specialized subagents, zero application code touched by the router.
...morelabwright
qgeng1465
A wet-lab design assistant whose numbers are computed and re-proved, never guessed. Verifiable wet-lab experimental design: organ-on-chip geometry, fluidics, dosing and statistics that an LLM can reason over without hallucinating.
...more@hasna-internal/kai-agent
andreihasna2
Agent interface, registry, initiator scope, and event vocabulary for the DeepSeek Harness
uk-law-agent
ssj4sunny
Cross-platform AI agent skill for UK legal research - legislation and case law from two public, unauthenticated sources. Installs into Claude Code, Cursor, Codex, Gemini CLI, GitHub Copilot, Windsurf, and 30+ other agents.
...more@yottameta/yotta-workflow
yottameta
Cross-session / cross-project workflow standard for all AI agents: read the state on start, store state nearby in a unified .workflow directory, persist logs/tasks/decisions while working, and leave a self-contained handoff anchor on finish. Triggers when
...moredsh-plugin-agent-dashboard
yytbit
Multi-agent dashboard skill for DeepSeek Harness -- status reports, task tracking, progress visualization
pi-verdict
GitHub Actions
A permission gate for Pi in the style of Claude Code's auto mode
dsh-playwright
jeremyguo
Use one shared Playwright browser together with your DeepSeek Harness AI.