Recursive Experiential–Working Memory Evolution for Long-Horizon Agent Harnesses
-
Updated
Aug 30, 2026 - Python
#
agent-harnesses
Agent harnesses are the runtime scaffolding around AI agents. They usually combine context delivery, tool interfaces, planning state, memory, sandboxes, permissions, evaluation, and observability so agents can complete longer tasks reliably. Agent harnesses are especially common in coding agents, research agents, and multi-agent workflows where repeatability, safety, and traceability matter.
Here are 11 public repositories matching this topic...
Open-source Python agent harness for auditable, cost-controlled LLM workflows with YAML playbooks and MCP server support.
python yaml audit-logs observability cost-management actor-critic-algorithm workflow-orchestration agent-framework llms ollama-api llm-agents agentic-ai ai-agents-automation model-context-protocol mcp-server litellm-ai-gateway claude-desktop-app agent-harnesses
-
Updated
Sep 15, 2026 - Python
Progressive-disclosure skill management across Codex, Claude Code, Cursor, Gemini, Hermes, and other agent harnesses.
cli automation backup restore gemini symlink developer-tools cursor hermes codex ai-agents progressive-disclosure github-copilot agent-skills claude-code agent-harnesses
-
Updated
Sep 16, 2026 - TypeScript
expert skill package for AI coding assistants working with the t1yOS Serverless platform.
serverless skills harness codex ai-agents cloud-functions ai-agent agentic-ai claude-code claude-code-skills claude-code-skill codex-skills agent-harness codex-skill ai-agent-skills harness-ai agent-harnesses dsh-plugin
-
Updated
Jul 11, 2026
A local workbench for recording, replaying, comparing, and inspecting tool-using agent runs without sending trace data to a hosted service.
-
Updated
Sep 9, 2026 - Python
Open-source framework for reproducible A/B evaluation of agent skills and instructions
python open-source benchmarking reproducible-research ab-testing ai-agents skill-evaluation prompt-engineering llm-evaluation coding-agents agent-evaluation agent-harnesses instruction-evaluation skivolve
-
Updated
Sep 14, 2026 - Python
Interlinked markdown wiki on agent harnesses, orchestration, formal methods, and adjacent research.
-
Updated
May 31, 2026 - TypeScript
DeepSeek Harness's desktop client.
-
Updated
Aug 15, 2026 - TypeScript
Codex skill for designing and scaffolding durable agent harness projects, with a Ralph Loop preset and upgrade-friendly doctrine.
developer-tools scaffolding codex ai-agents prompt-engineering agentic-workflows long-running-agents codex-skill ralph-loop harness-engineering project-presets agent-harnesses
-
Updated
Apr 8, 2026 - Python
An agent harness that carries a change from an intent to a branch you can merge — specified, produced in isolation, verified by your project's own commands, reviewed independently, accepted on evidence.
python cli developer-tools code-review software-engineering codex ai-agents claude ai-engineering llm local-llm ollama coding-agents agentic-ai claude-code spec-driven-development developer-tools-ai-agent harness-engineering agent-harnesses
-
Updated
Sep 15, 2026 - Python
Self-updating intelligence dashboard tracking the AI model and tooling landscape — frontier models, agent harnesses, self-hosting, strategy.
-
Updated
Aug 25, 2026 - Python
- Followers
- 168 followers
- Website
- github.com/topics/agent-harness