» Tag
agents
100 postsmemlineage v0.1.0: A Two-Layer Defense Against LLM Agent Memory Poisoning
memlineage v0.1.0 is an open-source Python library defending LLM agents against memory poisoning via cryptographic provenance and behavioral detection.
Building an LLM Wiki: Persistent Memory for AI Agents Over Live Sources
How one team built a self-updating LLM Wiki memory layer for AI agents, tackling live source drift and comparing grep, BM25, vector, and LLM retrieval.
Kira Project: a tamper-evident evidence layer for AI agents
Kira Project's tamper-evident evidence architecture separates AI agent logs from reports, cryptographically proving what happened and what didn't.
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.comWhy It's Hard to Make an AI Agent Truly Disagree
Building an AI agent whose sole job is to find flaws revealed how strongly LLMs default to agreeableness, and the prompt and architecture tricks needed to force real disagreement.
Why Coding Agents Stop Early on Long-Horizon Software Tasks
Explore why coding agents halt early in software tasks and proposed solutions.
Building AI Agents? Key Anti-Patterns to Avoid for Success
Learn about the anti-patterns that cause AI agent projects to fail and how to avoid them.
One of 1190 AI agent closing statements reports failure
A study shows that only one of 1190 AI closing statements reports failure, raising concerns about reliability for engineers.
The Bottleneck for AI Agents: It's Not the Model, It's the Context Layer
AI agents' issues stem from context layers, not models. Proper infrastructure can enhance reliability.
Vercel AI SDK 6's Agent Is Really Just a while Loop
A hands-on breakdown of how AI SDK 6's ToolLoopAgent and stopWhen actually control the agent loop, tested with a deterministic mock model.
Knowledge and Memory Management: First Three Directions Finalized
Knowledge-and-Memory-Management locks in its memory store, graph adapter, and persistence contracts—API stays backward-compatible while internals are rewritten.