» Tag
ai-agents
246 postsAI Coding Agents Are Breaking Diff-Based Code Review
AI coding agents make diff-only code review unreliable; intent now lives in test names, builder APIs, and contract tests instead.
Evaluation Debt: Why Offline Agent Evals Fail in Production
Why offline eval frameworks miss real production failures in AI agents, and why session-based observability is replacing static test suites.
A Unified Framework for Self-Improving Agent Systems
A conceptual framework unifying Skill evolution, harness adaptation, and self-referential evolution in self-improving AI agent systems, beyond model weights.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comBuilding Reliable Software With Untrustworthy AI Agents
A practical framework for reliable AI-agent coding: context window management, verification layers, CLAUDE.md briefs, and reusable skills.
ButterClaw: Self-Hosted Runtime Security for AI Agents, No Cloud
ButterClaw enforces AI agent security locally with regex signatures, a local LLM verdict pipeline, and SIGKILL/credential shredding — no cloud, no telemetry.
MCP goes stateless: the protocol's biggest update since launch
MCP's biggest update yet moves the protocol to a stateless architecture, adds a 12-month deprecation policy, and eyes enterprise-scale AI agents.
Ctxdiff Brings Git-Style Diffing to LLM Agent Context Windows
Ctxdiff is a local-first, open-source tool that applies git-style diffing to LLM agent context windows, turn by turn.
Toolgz cuts LLM tool-definition tokens by ~80% without accuracy loss
Toolgz reduces LLM tool-definition token usage by ~80% while preserving accuracy, validated across 420 runs on four frontier models.
@ttsc/graph: A Compiler-Built Code Graph MCP for AI Agents
@ttsc/graph is an MCP server using the TypeScript compiler's own type-check to build a code graph, cutting AI agent token use by about 90%.
Oversight Lints the Storybook Manifest Your AI Agent Actually Reads
Oversight, a new Storybook addon, lints the MCP manifest AI agents actually read, catching missing docs, extractor drift, and broken redirects.