-
Updated
Jan 8, 2026 - Python
#
long-horizon-ai
Here are 12 public repositories matching this topic...
EvoX Genesis is an autonomous system for long-horizon software evolution that recursively builds, continues, and transforms complex software from high-level objectives.
autonomous-agents long-term-memory evox agentic-framework agentic-ai vibecoding agentic-coding autonomous-coding agentic-os long-horizon-planning long-horizon-ai long-horizon-intelligence long-horizon-governance long-horizon-tasks long-horizon-agents autonomous-software-development
-
Updated
Sep 5, 2026 - Elixir
VLM-RL Hierarchical Loco-Manupilation For Long-Horizon Tasks With G1 robot in Isaac Lab/Sim
vlm g1 ppo semantic-map isaacsim loco-manipulation isaac-sim unitree long-horizon long-horizon-robotic-manipulation isaac-lab isaaclab unitree-g1 long-horizon-ai long-horizon-manipulation long-horizon-intelligence long-horizon-tasks
-
Updated
Aug 23, 2026 - Python
The simplest way to build long-horizon environments
-
Updated
Apr 8, 2026 - Python
An open-source autonomous AI agent that gets a Linux box and does whatever it wants.
agent open-source ai ted entity artificial-intelligence openai ai-agents agentic-ai long-horizon-ai openclaw
-
Updated
Apr 11, 2026 - HTML
Practitioner toolkit — templates, worked examples, and step-by-step guides for adopting LC-OS in your AI workflows.
templates longitudinal-studies ai-research field-manual applied-research ai-governance human-ai-collaboration ai-operating-system context-engineering ai-adoption ai-systems-design long-horizon-ai ai-alignment-practice collaboration-systems context-governance drift-prevention replication-kit
-
Updated
Jul 13, 2026 - JavaScript
Official code for Behavior-Skill, a fine-grained skill dataset and evaluation benchmark for Vision-Language-Action policies in long-horizon mobile manipulation tasks.
-
Updated
Sep 3, 2026 - Python
AI framework with human-inspired cognition, ethical reasoning, persistent memory, and context-grounded decision-making for accountable real‑world systems.
-
Updated
Apr 29, 2026 - Python
A governed cognition substrate: runtime infrastructure for persistent AI cognitive state under explicit governance. Nine primitives. 146 tests. Research prototype.
python state-management knowledge-management cognitive-architecture cognitive-systems ai-research contradiction-detection research-prototype ai-governance governed-cognition ai-reliability long-horizon-ai governance-first epistemic-state ai-substrate
-
Updated
Jun 24, 2026 - Python
Long-horizon AI harness you actually own: one static Go binary, one persona, any OpenAI-compat LLM (Ollama, Gemini, Claude, ChatGPT), MCP tools, chat via Telegram/Discord/Slack. Outbound-only — no dashboard, no config UI, no open ports, ever. Hardened so small local models finish tool calls.
golang telegram-bot mcp personal-assistant slack-bot harness harness-framework ai-agent llm long-horizon local-llm llm-tools ollama llm-agents model-context-protocol long-horizon-planning telegram-bot-ai-assistant long-horizon-ai long-horizon-tasks harness-ai
-
Updated
Sep 5, 2026 - Go
Architecture notes on CLI-native autonomous coding agents, tool runtimes, orchestration, UI surfaces, and protocols.
multi-agent-systems orchestrator autonomous-agents coding-agents agentic-workflow agent-orchestration subagents long-running-agents long-horizon-ai long-horizon-agents
-
Updated
May 21, 2026
AI-readable research archive on structural drift, role separation, and audit continuity in long-horizon human-AI research workflows.
research-workflows human-ai-interaction ai-assisted-research ai-readable long-horizon-ai role-separation bounded-archive structural-audit structural-drift audit-continuity
-
Updated
May 28, 2026
Add this topic to your repo
To associate your repository with the long-horizon-ai topic, visit your repo's landing page and select "manage topics."