DestructoR666 AI Digest · Free-source v0.3 no-repeat edit

Signal
Rag

Jun 21, 2026 63 leads scanned 4 sources
A tiny anti-slop zine for agents, tools, model ops, and actually useful AI weirdness. No X API toll paid.

Editor picks

Thinking, experiments, papers, and opinionated field notes first. Releases are useful, but they live downstairs now.
#01
Hacker News · hn · Jun 20

Show HN: Persona.js – a vanilla-JS agent UI library with native WebMCP (MIT)

Editor's read

A community-submitted project/thread. Plain version: Persona is an open-source, themeable AI chat widget you can add to any website in minutes.

Why you might care

MCP is becoming the plumbing layer for agent tools. Worth watching because it shapes what Hermes/OAC can connect to without bespoke glue code.

Source excerpt

Persona is an open-source, themeable AI chat widget you can add to any website in minutes. SSE streaming, agent loops, tool use, and style isolation: zero framework dependencies.

hnClaude Code agentdeep-summary
read57.8agent, mcp, tool use, claude code
#02
Hacker News · hn · Jun 19

Just made an app and MCP Server to convert Markdown to Google Docs

Editor's read

A community-submitted project/thread. A title-first lead about: Just made an app and MCP Server to convert Markdown to Google Docs. Skim it only if that maps to current agent/tooling work. Treat it as an early smoke signal, not a verdict. HN: 2 points, 1 comments. Query: Claude Code agent.

Why you might care

MCP is becoming the plumbing layer for agent tools. Worth watching because it shapes what Hermes/OAC can connect to without bespoke glue code.

Source excerpt

HN: 2 points, 1 comments. Query: Claude Code agent.

hnClaude Code agent
read48.8agent, mcp, claude code
#03
Hacker News · hn · Apr 22

Show HN: API Ingest – Agentic Search (Inter) API Docs

Editor's read

A community-submitted project/thread. Plain version: Handy MCP that converts API specs (OpenAPI YAML/JSON, RAML, WSDL, GraphQL, API Blueprint) into LLM-friendly markdown structures; focusing on token-efficiency and precision.

Why you might care

MCP is becoming the plumbing layer for agent tools. Worth watching because it shapes what Hermes/OAC can connect to without bespoke glue code.

Source excerpt

Handy MCP that converts API specs (OpenAPI YAML/JSON, RAML, WSDL, GraphQL, API Blueprint) into LLM-friendly markdown structures; focusing on token-efficiency and precision.

hnLLM eval benchmarkdeep-summary
read44.0agent, mcp, eval, benchmark
#04
arXiv · paper · Jun 18

Observation of electroweak production of pairs of Z bosons in proton-proton collisions at 13 TeV

Editor's read

A research paper. In human terms: The first evidence of electroweak (EW) production of pairs of Z bosons in association with two jets (jj) in the final state ZZjj $\to$ $\ell\ellνν$jj, where $\ell$ = e, $μ$, is reported by the CMS experiment.

Why you might care

This maps directly onto OAC: what agents remember, what they should forget, and how not to build a cursed context landfill.

Source excerpt

The first evidence of electroweak (EW) production of pairs of Z bosons in association with two jets (jj) in the final state ZZjj $\to$ $\ell\ellνν$jj, where $\ell$ = e, $μ$, is reported by the CMS experiment. The analysis is based on a data sample of proton-proton (pp) collisions at $\sqrt{s}$ = 13 TeV, corresponding to an integrated luminosity of 138 fb$^{-1}$. Events are selected by requiring exactly two leptons o…

paperlarge language model agents memoryhep-ex
paper shelf31.0agent, agents, memory
#05
arXiv · paper · Jun 18

Optimal Deterministic Multicalibration and Omniprediction

Editor's read

A research paper. In human terms: A model is multicalibrated on a collection of group weights $G$ if it is calibrated -- i.e.

Why you might care

Probably not bedtime reading, but papers can reveal new primitives before they become tools. Skim the abstract; deep-read only if it smells buildable.

Source excerpt

A model is multicalibrated on a collection of group weights $G$ if it is calibrated -- i.e. unbiased even conditional on its prediction -- not just overall, but also after reweighting contexts by each $g \in G$. It is a useful property for many downstream applications and is a basic desideratum of trustworthy machine learning. Before this work, all predictors known to attain the minimax-optimal $\widetilde O(\vareps…

paperagentic AI tool usecs.LGmath.ST
paper shelf24.0agent, tool use

Articles / research / opinions

The stuff people are thinking, trying, arguing, and building with the tech. This is the main read pile.
#06
arXiv · paper · Jun 18

Thinking in Boxes: 3D Editing in Real Images Made Easy

Editor's read

A research paper. In human terms: Text and 2D-conditioning interfaces provide weak, ambiguous control over spatial transformations in image editing -- particularly under large object motions and camera changes.

Why you might care

Probably not bedtime reading, but papers can reveal new primitives before they become tools. Skim the abstract; deep-read only if it smells buildable.

Source excerpt

Text and 2D-conditioning interfaces provide weak, ambiguous control over spatial transformations in image editing -- particularly under large object motions and camera changes. Prior work has used 3D primitives such as boxes, but only as loose conditioning signals indicating approximate object location rather than specifying the transformation. We instead use 3D boxes as structured specifications: the user provides…

paperagentic AI tool usecs.CV
paper shelf24.0agent, tool use
#07
Google DeepMind Blog · feed · Jun 10

Investing in multi-agent AI safety research

Editor's read

A post from Google DeepMind Blog. Plain version: Google DeepMind and partners announce a $10M funding call for multi-agent safety research.

Why you might care

Kept because it matched the radar’s AI/agent/tooling filters. Skim title + source first; open only if it lines up with current Hermes/OAC work.

Source excerpt

Google DeepMind and partners announce a $10M funding call for multi-agent safety research.

researchmodels
maybe18.0feed
#08
Google DeepMind Blog · feed · Jun 9

Fluid, natural voice translation with Gemini 3.5 Live Translate

Editor's read

A post from Google DeepMind Blog. Plain version: Gemini 3.5 Live Translate brings near real-time, natural speech translation to Google AI Studio, Google Translate and Google Meet.

Why you might care

Kept because it matched the radar’s AI/agent/tooling filters. Skim title + source first; open only if it lines up with current Hermes/OAC work.

Source excerpt

Gemini 3.5 Live Translate brings near real-time, natural speech translation to Google AI Studio, Google Translate and Google Meet.

researchmodels
maybe18.0feed
#09
Google DeepMind Blog · feed · Jun 9

Introducing Gemma 4 12B: a unified, encoder-free multimodal model

Editor's read

A post from Google DeepMind Blog. Plain version: An overview of Gemma 4 12B, a model designed to bring high-performance multimodal intelligence directly to your laptop.

Why you might care

Kept because it matched the radar’s AI/agent/tooling filters. Skim title + source first; open only if it lines up with current Hermes/OAC work.

Source excerpt

An overview of Gemma 4 12B, a model designed to bring high-performance multimodal intelligence directly to your laptop.

researchmodelsdeep-summary
maybe18.0feed
#10
Hacker News · hn · Jun 20

Show HN: I built a middleware agent that turns PLC data into REST/gRPC APIs

Editor's read

A community-submitted project/thread. Plain version: Limen Edge is a self-hosted edge agent that turns raw PLC data into clean REST and gRPC APIs.

Why you might care

MCP is becoming the plumbing layer for agent tools. Worth watching because it shapes what Hermes/OAC can connect to without bespoke glue code.

Source excerpt

Limen Edge is a self-hosted edge agent that turns raw PLC data into clean REST and gRPC APIs. Modbus TCP, OPC UA, EtherNet/IP. No cloud required.

hnMCP agent LLMdeep-summary
read43.7agent, mcp
#11
Hacker News · hn · Jun 20

Show HN: We post-trained a model that pen tests instead of refusing

Editor's read

A community-submitted project/thread. Plain version: Audit your code with a read-only Security Scan, or run a gated Pen Test against systems you authorise.

Why you might care

HN is noisy, but comments surface implementation pain fast. Good for spotting whether a shiny thing survives contact with engineers.

Source excerpt

Audit your code with a read-only Security Scan, or run a gated Pen Test against systems you authorise. Same CLI, two modes. Free on repos you own; pen test by request.

hnAI agents tool usedeep-summary
read43.3agent, agents, tool use
#12
Hacker News · hn · Jun 19

Show HN: Timestamp and provenance records for AI-assisted creative work

Editor's read

A community-submitted project/thread. Plain version: Create timestamped public proof for AI-assisted work before you publish, pitch, or deliver it.

Why you might care

HN is noisy, but comments surface implementation pain fast. Good for spotting whether a shiny thing survives contact with engineers.

Source excerpt

Create timestamped public proof for AI-assisted work before you publish, pitch, or deliver it.

hnAI agents tool usedeep-summary
read42.2agent, agents, tool use
#13
Hacker News · hn · Jun 18

Show HN: Coding Tools MCP – Give any LLM agent the ability to code

Editor's read

A community-submitted project/thread. Plain version: Coding Tools MCP is a model-neutral coding-agent runtime MCP server.

Why you might care

MCP is becoming the plumbing layer for agent tools. Worth watching because it shapes what Hermes/OAC can connect to without bespoke glue code.

Source excerpt

Coding Tools MCP is a model-neutral coding-agent runtime MCP server. It exposes local coding primitives to any MCP client:

hnMCP agent LLMdeep-summary
skim40.8agent, mcp
#14
Hacker News · hn · May 19

Show HN: Forge – Guardrails take an 8B model from 53% to 99% on agentic tasks

Editor's read

A community-submitted project/thread. Plain version: A Python framework for self-hosted LLM tool-calling and multi-step agentic workflows - antoinezambelli/forge

Why you might care

Evals are how we avoid vibes-only agent work. Useful if it suggests tests we can adapt for Hermes/OAC reliability.

Source excerpt

A Python framework for self-hosted LLM tool-calling and multi-step agentic workflows - antoinezambelli/forge

hnLLM eval benchmarkdeep-summary
skim37.0agent, eval, benchmark, workflow

Releases / software updates

Important for staying current, but intentionally below the longform material. Changelogs are seasoning, not dinner.
#01
GitHub · release · Jun 19

Hermes Agent: Hermes Agent v0.17.0 (v2026.6.19)

Release note

A new release/update from Hermes Agent. Plain version: The Reach Release. v0.16.0 put Hermes on your desktop. v0.17.0 is about how far that reach extends — across new places to…

Why you might care

Directly relevant to your agent stack. This can affect Hermes behavior, upgrade timing, plugins, gateway surfaces, or ideas worth stealing for OAC/DestructoR666.

Source excerpt

# Hermes Agent v0.17.0 (v2026.6.19) **Release Date:** June 19, 2026 **Since v0.16.0:** ~1,475 commits · ~800 merged PRs · 1,693 files changed · 235,390 insertions · 50,730 deletions · 300+ issues closed · 245 community contributors > **The Reach Release.** v0.16.0 put Hermes on your desktop. v0.17.0 is about how far that reach extends — across new places to…

hermesagent-opsNousResearch/hermes-agent
watch release57.0hermes, hermes
#02
GitHub · release · May 26

OpenAI Agents Python: v0.17.4

Release note

A new release/update from OpenAI Agents Python. Plain version: feat: support Realtime custom voice objects by @lionel-oai in * fix: #3459 add opt-in recovery for missing function tools by @seratch in * fix: apply hardened http client default to MCP SSE transport by @ioleksiuk in

Why you might care

Competitive intel: how OpenAI thinks agent SDKs should work, where Hermes is ahead/behind, and patterns we might borrow without joining the mothership.

Source excerpt

## What's Changed * feat: support Realtime custom voice objects by @lionel-oai in https://github.com/openai/openai-agents-python/pull/3473 * fix: #3459 add opt-in recovery for missing function tools by @seratch in https://github.com/openai/openai-agents-python/pull/3461 * fix: apply hardened http client default to MCP SSE transport by @ioleksiuk in https://…

agentssdkopenai/openai-agents-python
watch release51.0agent, agents, mcp, openai agents
#03
GitHub · release · Jun 5

Hermes Agent: Hermes Agent v0.16.0 (2026.6.5) — The Surface Release

Release note

A new release/update from Hermes Agent. Plain version: The Surface Release. Hermes meets you wherever you work. A brand-new na…

Why you might care

Directly relevant to your agent stack. This can affect Hermes behavior, upgrade timing, plugins, gateway surfaces, or ideas worth stealing for OAC/DestructoR666.

Source excerpt

# Hermes Agent v0.16.0 (v2026.6.5) **Release Date:** June 5, 2026 **Since v0.15.2:** 874 commits · 542 merged PRs · 1,962 files changed · 205,216 insertions · 46,217 deletions · 399 issues closed (2 P0, 62 P1, 16 security-tagged) · 170 community contributors (including co-authors) > **The Surface Release.** Hermes meets you wherever you work. A brand-new na…

hermesagent-opsNousResearch/hermes-agent
watch release48.0hermes, hermes
#04
GitHub · release · Jun 19

OpenAI Agents Python: v0.17.6

Release note

A new release/update from OpenAI Agents Python. Plain version: feat: add pre-approval tool input guardrails by @seratch in * feat: add SDK-only custom data for tool outputs by @seratch in * fix: enforce the documented strict JSON-compatible contract for #3486 by @siddiksawani in

Why you might care

Competitive intel: how OpenAI thinks agent SDKs should work, where Hermes is ahead/behind, and patterns we might borrow without joining the mothership.

Source excerpt

## What's Changed * feat: add pre-approval tool input guardrails by @seratch in https://github.com/openai/openai-agents-python/pull/3487 * feat: add SDK-only custom data for tool outputs by @seratch in https://github.com/openai/openai-agents-python/pull/3486 * fix: enforce the documented strict JSON-compatible contract for #3486 by @siddiksawani in https://…

agentssdkopenai/openai-agents-python
skim changelog38.0agents, openai agents
#05
GitHub · release · Jun 18

LangGraph: langgraph==1.2.6

Release note

A new release/update from LangGraph. Plain version: 1.2.5 * release(langgraph): 1.2.6 (#8139) * fix: nested subgraph inherits parent checkpoint_ns (regression in 1.2.3) (#8053) * fix: cancel running subgraphs on v3 stream abort [closes #8029] (#8057) * release(cli): 0.4.30 (#8101)…

Why you might care

Useful as a contrast model for workflow/stateful agents. Even if we do not adopt it, it exposes design patterns and footguns for OAC-style continuity.

Source excerpt

Changes since 1.2.5 * release(langgraph): 1.2.6 (#8139) * fix: nested subgraph inherits parent checkpoint_ns (regression in 1.2.3) (#8053) * fix: cancel running subgraphs on v3 stream abort [closes #8029] (#8057) * release(cli): 0.4.30 (#8101) * docs: standardize package `README.md` structure (#8064) * chore(deps): bump tornado from 6.5.5 to 6.5.6 in /libs/…

agentsworkflowlangchain-ai/langgraph
skim changelog37.3agents, workflow
#06
GitHub · release · Apr 1

MCP TypeScript SDK: @modelcontextprotocol/node@2.0.0-alpha.1

Release note

A new release/update from MCP TypeScript SDK. Plain version: Patch Changes - #1504 327243c Thanks @corvid-agent!

Why you might care

MCP is becoming the plumbing layer for agent tools. Worth watching because it shapes what Hermes/OAC can connect to without bespoke glue code.

Source excerpt

### Patch Changes - [#1504](https://github.com/modelcontextprotocol/typescript-sdk/pull/1504) [`327243c`](https://github.com/modelcontextprotocol/typescript-sdk/commit/327243cebd96e07686c88f7fa9ca22a5a7a7993d) Thanks [@corvid-agent](https://github.com/corvid-agent)! - Add missing `hono` peer dependency to `@modelcontextprotocol/node`. The package already de…

mcptoolsmodelcontextprotocol/typescript-sdk
skim changelog37.0agent, mcp
#07
GitHub · release · Jun 16

MCP Python SDK: v2.0.0a2

Release note

A new release/update from MCP Python SDK. Plain version: Full 2026-07-28 types added…

Why you might care

MCP is becoming the plumbing layer for agent tools. Worth watching because it shapes what Hermes/OAC can connect to without bespoke glue code.

Source excerpt

Second v2 alpha. Pre-releases are opt-in only; `pip install mcp` still resolves to the stable 1.x line. ```bash pip install mcp==2.0.0a2 # or uv add "mcp==2.0.0a2" ``` See the [migration guide](https://github.com/modelcontextprotocol/python-sdk/blob/main/docs/migration.md) for the full list of breaking changes. ## Highlights ### Full 2026-07-28 types added…

mcptoolsmodelcontextprotocol/python-sdk
skim changelog33.7mcp
#08
GitHub · release · Jun 16

MCP Python SDK: v1.28.0

Release note

A new release/update from MCP Python SDK. Plain version: Deprecations Two API surfaces now emit DeprecationWarning ahead of their removal in v2.

Why you might care

MCP is becoming the plumbing layer for agent tools. Worth watching because it shapes what Hermes/OAC can connect to without bespoke glue code.

Source excerpt

## Deprecations Two API surfaces now emit `DeprecationWarning` ahead of their removal in v2. Nothing is removed in 1.x, and the warnings fire only when the deprecated API is *called* - importing the modules stays silent. - **WebSocket transport** - `mcp.client.websocket.websocket_client` and `mcp.server.websocket.websocket_server`. WebSocket was never part…

mcptoolsmodelcontextprotocol/python-sdk
skim changelog33.7mcp
#09
GitHub · release · Jun 16

LangGraph: langgraph-cli==0.4.30

Release note

A new release/update from LangGraph. Plain version: cli==0.4.29 * release(cli): 0.4.30 (#8101) * feat(cli): support compatible api version ranges (#8023) * docs: standardize package README.md structure (#8064)

Why you might care

Useful as a contrast model for workflow/stateful agents. Even if we do not adopt it, it exposes design patterns and footguns for OAC-style continuity.

Source excerpt

Changes since cli==0.4.29 * release(cli): 0.4.30 (#8101) * feat(cli): support compatible api version ranges (#8023) * docs: standardize package `README.md` structure (#8064)

agentsworkflowlangchain-ai/langgraph
skim changelog33.6agents, workflow
#10
GitHub · release · Apr 1

MCP TypeScript SDK: @modelcontextprotocol/server@2.0.0-alpha.2

Release note

A new release/update from MCP TypeScript SDK. Plain version: Patch Changes - #1840 424cbae Thanks @KKonstantinov!

Why you might care

MCP is becoming the plumbing layer for agent tools. Worth watching because it shapes what Hermes/OAC can connect to without bespoke glue code.

Source excerpt

### Patch Changes - [#1840](https://github.com/modelcontextprotocol/typescript-sdk/pull/1840) [`424cbae`](https://github.com/modelcontextprotocol/typescript-sdk/commit/424cbaeee13b7fe18d38048295135395b9ad81bb) Thanks [@KKonstantinov](https://github.com/KKonstantinov)! - tsdown exports resolution fix

mcptoolsmodelcontextprotocol/typescript-sdk
skim changelog30.0mcp

Radar stats

V0 uses dumb-but-transparent scoring. Future versions can add LLM judgment after collection is bounded.
63total leads
24printed
4sources hit
$0X API spend
9feed20hn4paper30release

Editorial stance

Twitter is a goblin with binoculars, not the editorial board. V0 watches free sources first: RSS, GitHub, HN, arXiv. Articles, research, and opinionated field notes get top billing; releases are parked lower because staying current matters, but changelog spelunking is not a personality.

Collector logs

Receipts and failures. The web remains held together by raccoon string.