AI directory search

Search across educators, skills, and resources.

Use this when you know the topic you need: Claude Code, MCP, evals, RAG, agents, product, coding, prompting, foundations, or model internals.

6 matches for "compaction"

Resources

Introducing the Agents API

Managed agent API launch and guide · OpenAI · Intermediate to advanced

You want OpenAI's September 10, 2026 launch guide for building long-running cloud agents with the managed Codex harness, context compaction, tool search, multi-agent delegation, and your choice of hosted or self-managed sandbox.

openai, agents, codex, context compaction, multi-agent

OpenAI Codex hooks

Coding agent guide · OpenAI · Intermediate to advanced

You need lifecycle hooks that run scripts or MCP tools around Codex sessions, prompts, tool calls, compaction, subagents, permissions, validation, logging, or persistent-memory workflows.

openai, codex, hooks, mcp, automation

Prompting Claude Fable 5.1

Prompting guide · Anthropic · Intermediate to advanced

You are testing or migrating to Claude Fable 5.1 and want model-specific guidance for effort, progress updates, tool-call batching, long tasks, compaction, subagents, file edits, and verification.

anthropic, claude fable 5.1, prompting, coding agents, tool use

OpenAI compaction guide

Guide · OpenAI · Intermediate

You need the official pattern for compressing long agent conversations and preserving the right context instead of letting transcripts grow until quality or cost breaks down.

openai, compaction, context management, long-running agents, reasoning

xAI Context Compaction

Guide · xAI · Intermediate to advanced

You want xAI's official guidance for shrinking long conversations into reusable compact state before teaching Grok-heavy agent workflows at scale.

xai, context compaction, agents, long context, cost optimization

A Local-First Agent for Private and Cost-Effective Knowledge Work

Engineering study · Perplexity · Intermediate to advanced

You want a practical primary-source study of co-designing a compact local model and agent harness, including on-demand skills, context compaction, sandboxing, verification, and optional frontier-model escalation.

perplexity, local models, agent harnesses, privacy, sandboxing