VultrVultr
返回目录

GITHUB TOPIC

context-engineering

7个项目包含此标签

7 个项目

GitHub Topic 精确匹配

Agent 与会话技能

Use this cross-platform skill in Codex or Claude Code to establish repository-local continuity memory so a future agent can recover objective, status, decisions, validation, risks, and next actions without relying on previous chat history.

待结构检查
agent-handoffagent-skillsclaude-codecodex
模型与 MCP插件

dsh-mcp-lens

labmimors

DeepSeek Harness MCP tool search for large catalogs: 1,000 MCP tools behind 2 MCP-facing schemas, exact-schema calls, allow/deny controls, and a local calculator.

待结构检查
agent-harnesscontext-engineeringcontext-optimizationcontext-reduction
Agent 与会话技能

Baton

kakadeka

Pass your project, not your context.

待结构检查
ai-agentsai-memoryclaude-codeclaude-skills
Agent 与会话插件

Execution-time drift firewall for long-running DeepSeek Harness agents. Real-Harness tests: unsafe stale mutations 12/12 native -> 0/12; valid controls 7/7 both; post-SIGKILL unsafe continuation 2/2 -> 0/2.

待结构检查
agent-harnessagent-orchestrationagent-planningagent-safety
Agent 与会话插件

AgentNavi

CoaseEdge

The navigation of AI Agent.

待结构检查
agent-memoryai-agentclaude-codecodex
模型与 MCP插件

dsh-mcp-lens

Andrietteprotective835

Shrink massive MCP catalogs to two tools, letting DeepSeek Harness search and call 1,000+ remote APIs efficiently.

待结构检查
ai-toolingcontext-engineeringcontext-optimizationcontext-reduction
Agent 与会话插件

dsh-precedent

dshplugin-me

Evidence-backed working memory for DeepSeek Harness: a cited ledger of what already worked in this workspace, built from the session log you already have. No index, no model, no capture step.

待结构检查
agent-memorycontext-engineeringdeepseek-harnessdsh-plugin