Library
Research, decisions, and patterns extracted from real agent sessions.
Multi-Agent Frameworks: Five Bets, Three Categories, One Decision
Anthropic Managed Agents, LangGraph, CrewAI, OpenAI Agents SDK, and Flue solve the same surface problem with five very different bets. Three categories: hosted runtime, library/orchestrator, harness primitive. Same workflow spiked across all five (cd6 code review, 890 LOC of working spike code) shows the LOC tax for each framework's distinctive value layer — and where each one actually earns it. Side-by-side matrix, programming-model shapes, cost crossover analysis, and the question your team is actually answering.
Agent Infrastructure Foundation: 12 Interfaces, Commodity Backends, Empty-Diff Exit Gate
Harness engineering named the architecture above the model. This is the buildable form. 12 stable interfaces a small platform team owns, backends as commodity rentals, a 6-week POC with one honest exit gate: a different engineer ships the second workflow with zero foundation diff.
Flue: When the Astro Team Builds a Headless Claude Code
The withastro org shipped Flue — a TypeScript framework that takes Claude Code's harness shape (sandbox, tools, sessions, skills, AGENTS.md), strips the TUI, and makes it deployable to Node.js or Cloudflare Workers from the same source. This is what 'agents are directories that compile to servers' looks like in practice. v0.3.5, Apache-2.0, 7,013 SDK lines, zero tests.
GitAgent: The Open Standard for Defining AI Agents as Git Repos
GitAgent defines AI agents as version-controlled files in a git repository. Define once, export to Claude Code, OpenAI, CrewAI, Gemini, and 12+ frameworks. With a built-in registry, compliance support, and composable skills ecosystem.
Building Your Org's Agent Harness: The Practical Guide
Same model, different harness, 14-point improvement. Stripe ships 1,300 PRs/week. Spotify uses 3 tools, not 300. Here's how to build the org-specific agent harness that compounds into your competitive moat — starting with 60 lines of markdown.
Harness Engineering & Deep Agents: The Architecture Layer Above Context Engineering
LangChain's Deep Agents SDK codifies four primitives (planning, subagents, filesystem, detailed prompts) observed in Claude Code, Manus, and Deep Research. OpenAI coined 'harness engineering' — the complete system wrapping an agent. Here's the full landscape, the evidence, and what it means for how agents are built in 2026.
Programmatic Tool Calling: How AI Agents Learned to Use Your Computer
From autocomplete to autonomous agents. The evolution of AI tool calling — from Copilot's inline suggestions to Claude Code's bash execution, sub-agents, and MCP integration. What changed, what it means for developers, and where the evidence actually points.
Context Engineering: Why It's Replacing Prompt Engineering
Gartner says context engineering is replacing prompt engineering for enterprise AI. Anthropic, LangChain, and practitioners agree: most agent failures are context failures, not model failures. Here's what it actually means, what the evidence says, and what to do about it.
The Epistemological Crisis: AI Codes Faster Than We Can Think
Anthropic's controlled study shows 17% comprehension decrease with AI assistance. Karpathy admits skill atrophy. Most developers use AI code they don't understand. The crisis isn't about AI quality—it's about knowledge management at AI speed.
Git Context Controller: Version-Controlled Memory for LLM Agents
An Oxford paper treats agent memory like Git—commit, branch, merge, context. Achieves 48% on SWE-Bench-Lite, outperforming 26 systems. We contextualize the findings against Tacit's session intelligence and what this means for persistent agent memory.
LLM Context Optimization: What Actually Works
A 200K context window doesn't mean 200K effective tokens. Research across academic papers, production systems (Claude Code, Codex CLI, Amp), and benchmarks reveals when to trim, summarize, cache, or delegate—and the pitfalls that break real agents.
10 Tips from the Claude Code Team
Battle-tested workflows from Boris Cherny—Claude Code's creator—and his team. Parallel worktrees, evolved CLAUDE.md files, subagents, and the practices that ship 259 PRs in 30 days.
The AI Coding Phase Shift: A Multi-Perspective Analysis
When the architect of GPT and Tesla Autopilot says AI is changing how he codes—and degrading his skills—four expert perspectives examine what this means for the rest of us.
AI Code Review: Is It Really the Bottleneck?
Evidence-based analysis of whether code review has become the new bottleneck in AI-assisted development. Tool comparisons, cognitive limits, and risk assessment.
Every artifact here was extracted from real sessions using Tacit. Get Tacit to create your own.