Search: github.com/esc | Heykuki News

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

361.

Disguise Yourself with CyberFlare

1 point

13 years ago

362.

Show HN: Govern Anthropic Managed Agents with 3 lines of code

1 point

a month ago

363.

Show HN: The Trawl CLI, trudge through agent harness logs for shit and giggles (the-daily-claude.github.io)

1 point

2 months ago

364.

Show HN: Open-source white-box agentic red teamer for AI agents (github.com/sundi133)

1 point

3 months ago

365.

Show HN: PromptSonar – Static analysis for LLM prompt security (github.com/meghal86)

1 point

3 months ago

366.

Show HN: Tokf – Stop wasting LLM context on verbose build output (github.com/mpecan)

1 point

3 months ago

367.

Show HN: KarnEvil9, a deterministic AI agent runtime (github.com/oldeucryptoboi)

1 point

3 months ago

368.

Show HN: Modeled healthcare de-identification as longitudinal RL control problem (github.com/azithteja91)

1 point

3 months ago

369.

Show HN: Telos – eBPF/LSM Runtime Security for Autonomous AI Agents (github.com/nevinshine)

1 point

3 months ago

370.

Show HN: A resume renderer that auto-fits your content to one page

1 point

3 months ago

371.

Show HN: AI sandbox that runs on your homelab (github.com/deevus)

1 point

3 months ago

372.

Show HN: AliveUI – CSS framework with motion and depth as first-class primitives (aliveui.dev)

1 point

3 months ago

373.

Show HN: Upjack – Declarative framework for building apps over MCP (github.com/NimbleBrainInc)

1 point

barefootsanders

3 months ago

374.

Show HN: ClawMoat – Open-source runtime security for AI agents (zero deps, <1ms) (github.com/darfaz)

1 point

3 months ago

375.

Show HN: Jsonchunk – Parse incomplete JSON from streaming LLM responses (github.com/jbingen)

1 point

3 months ago

376.

We audited both MCP SDKs – three classes of boundary-crossing vulnerabilities

1 point

3 months ago

377.

Show HN: OmniGlass – An open-source, sandboxed Visual Action Engine (github.com/goshtasb)

1 point

3 months ago

378.

Show HN: Plyra-guard – intercepts AI agent tool calls before execution (github.com/plyraAI)

1 point

3 months ago

379.

Show HN: Attest – Test AI agents with 8-layer graduated assertions

1 point

3 months ago

380.

Show HN: HexaScan:Open-Source Monitoring(PageSpeed,Critical Flows,SEO,Security) (github.com/BlazeHexaScan)

1 point

4 months ago

381.

Show HN: Claude Code as a Doctor for Claude Code (github.com/Ramsbaby)

1 point

4 months ago

382.

Show HN: AI alignment is an infrastructure problem

1 point

4 months ago

383.

How to Red Team Your AI Agent in 48 Hours – A Practical Methodology

1 point

4 months ago

384.

Show HN: DoScript – DSL for file automation with natural language syntax (github.com/TheServer-lab)

1 point

4 months ago

385.

Show HN: Agent Hypervisor – Reality Virtualization for AI Agents (github.com/sv-pro)

1 point

4 months ago

386.

Show HN: OneUptime – Open-source observability that auto-fixes incidents with AI

1 point

4 months ago

387.

The OWASP LLM Top: A Practical Attack Guide (with 122 real attack techniques)

1 point

4 months ago

388.

Show HN: Kore – Stack based language where compiler is the reward function (github.com/konf-dev)

1 point

4 months ago

389.

Show HN: Hybrid Orchestrator – Reliable AI agents for finance (github.com/pavelsukhachev)

1 point

4 months ago

390.

Show HN: AgentLink – AI agents earn SOL on Solana via skill.md protocol (theagentlink.xyz)

1 point

4 months ago