AlphaSignal
Subscribe
Sign in
Home
Notes
Archive
About
Latest
Top
Discussions
How OpenHuman Works, And How to Set It Up in 5 Minutes
The open-source desktop agent that crossed +20k GitHub stars in days, what’s inside, and the full walkthrough.
23 hrs ago
•
AlphaSignal AI
1
1
RAG and Long Context Aren't Enough for Agent Memory. δ-mem Is a Third Option
An 8×8 online state lifted Qwen3-4B from 46.79% to 51.66%, with the backbone untouched.
May 20
•
AlphaSignal AI
11 Open-Source Repos Every AI Infra Engineer Should Bookmark
You built an AI agent this weekend. Have you thought about its infrastructure?
May 19
•
AlphaSignal AI
1
1
Hermes Just Made Codex the Engine and Itself the Shell.
Opt-in beta in Hermes 2026.5. One slash command, three tool sources, four tools left behind.
May 18
•
AlphaSignal AI
How LLMs Compute the Right Answer, Then Match the Swarm’s Wrong One, and How to Wire Around It
A single peer auditor dropped GPT-5.4 from 98% to 10% across 22,500 Waterloo trajectories.
May 15
•
AlphaSignal AI
Researchers Just Counted 146,932 Hallucinated Citations. This Repo Is the First Installable Fix
Academic Research Skills: 4 Claude Code skills, 25 modes, two integrity gates, CC BY-NC 4.0
May 14
•
AlphaSignal AI
How agentmemory works, and how to actually use it to with your agent
Trending, 12 hooks, 51 MCP tools, and a triple-stream retrieval pipeline that scores 95.2% R@5 on LongMemEval-S
May 13
•
AlphaSignal AI
1
How AI Agents Follow Senior-Engineer Production Workflows, How to Wire It Into Your Stack
22 Markdown skills, 7 slash commands, and the author bet that the harness matters more than the model.
May 12
•
AlphaSignal AI
1
When AI agents learn to engineer themselves
A primer on self-improving agents: Moving beyond the human-coded harness
May 12
•
AlphaSignal AI
1
You Should Install Hermes Agent This Weekend
Cheap 1M-context models changed the model layer. Claude Code and Codex changed the coding layer. Hermes is starting to look like the runtime layer.
May 11
•
AlphaSignal AI
+29k Stars, No Vectors: How PageIndex Replaces Embeddings With LLM Reasoning
VectifyAI’s tree-based RAG hits 98.7% on FinanceBench. The MCTS the docs mention isn’t in the open-source code.
May 8
•
AlphaSignal AI
How HeavySkill Turns Agentic Harness Tricks Into a One-File Inner Skill
Two-stage protocol from Meituan, R1-Distill-Qwen3-8B goes 35.7% → 69.3% on IFEval
May 7
•
AlphaSignal AI
2
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts
