Search: github.com/eval | Heykuki News

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

961.

Show HN: Lodmem – Level of Detail Context Management for Agents (github.com/agenteractai)

2 points

2 months ago

962.

Show HN: SkillCompass – Diagnose and Improve AI Agent Skills Across 6 Dimensions (github.com/Evol-ai)

2 points

2 months ago

963.

Show HN: OpenClaw Arena – Benchmark models on real tasks, rank by perf and cost (app.uniclaw.ai)

2 points

2 months ago

964.

Show HN: Image Ranker – Open-Source Pairwise Ranking for Preference Learning (github.com/QuentinWach)

2 points

2 months ago

965.

Show HN: Tested 12 LLMs with few-shot examples

2 points

2 months ago

966.

Show HN: Perstack – Containerized harness, 5 tests with full logs and API cost (github.com/perstack-ai)

2 points

3 months ago

967.

Show HN: LocalAgent v0.5.0, a local-first Rust agent runtime (github.com/CalvinSturm)

2 points

3 months ago

968.

Show HN: A test harness that blocks unsafe AI actions before execution

2 points

celestinestudio

3 months ago

969.

Show HN: Wikimetron – Surface hidden sensitivity and risk in Wikipedia (github.com/opinionscience)

2 points

3 months ago

970.

Show HN: HDC-based function caller ranks #2 on BFCL V4 – $2.08 vs. Opus at $87 (github.com/glyphh-ai)

2 points

3 months ago

971.

Show HN: AlphaEvolve inspired evolution harness for Pokemon (github.com/papercomputeco)

2 points

3 months ago

972.

Show HN: Aegis – Open-source pre-execution firewall for AI agents (github.com/Justin0504)

2 points

3 months ago

973.

Show HN: Yardstiq – Compare LLM outputs side-by-side in your terminal (yardstiq.sh)

2 points

3 months ago

974.

Show HN: I built an MCP server to recruit employees for free (github.com/Himalayas-App)

2 points

3 months ago

975.

Show HN: Chromectl – CLI to give an AI agent its own Chrome session (github.com/BartlomiejLewandowski)

2 points

3 months ago

976.

Show HN: Open Vernacular AI Kit – preprocessing for Indian code-mixed text (github.com/SudhirGadhvi)

2 points

3 months ago

977.

Show HN: Decision Guardian – Auto-surface architectural context on PRs and CLI

2 points

3 months ago

978.

Show HN: Lar-JEPA – A Testbed for Orchestrating Predictive World Models (github.com/snath-ai)

2 points

3 months ago

979.

Show HN: Batchling – save 50% off any GenAI requests in two lines of code (github.com/vienneraphael)

2 points

3 months ago

980.

Show HN: BreakMyAgent – Open-source red-teaming sandbox for LLM system prompts

2 points

3 months ago

981.

Show HN: Edictum – Runtime governance for LLM agent tool calls

2 points

3 months ago

982.

Show HN: GrowthClaw, a workflow pack for deterministic growth execution (github.com/mrrkrieg)

2 points

4 months ago

983.

Show HN: Agentic Gatekeeper – AI pre-commit hook to auto-patch logic errors (github.com/revanthpobala)

2 points

4 months ago

984.

Show HN: LocalAgent: local coding agent CLI with trust and replay (github.com/CalvinSturm)

2 points

4 months ago

985.

Ask HN: How would you distribute a privacy-first AI chat for teams?

2 points

4 months ago

986.

Show HN: I maintain Valkey GLIDE – built a Node queue doing 48k jobs/s (github.com/avifenesh)

2 points

4 months ago

987.

Show HN: Banish – A declarative DSL for rule-based state machines in Rust (github.com/LoganFlaherty)

2 points

4 months ago

988.

Show HN: Code Scalpel – AST analyzer and security scanner (MCP server) (codescalpel.dev)

2 points

4 months ago

989.

Show HN: Tori Terminal-native Docker monitoring with alerting in a single binary (github.com/thobiasn)

2 points

4 months ago

990.

Show HN: Wax – RAG in a single file (SQLite for AI memory) (github.com/christopherkarani)

2 points

4 months ago