Search: github.com/eval | Heykuki News

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

631.

Show HN: Terminal-Bench-RL: Training long-horizon terminal agents with RL (github.com/Danau5tin)

125 points

10 months ago

632.

Show HN: CLI that spots fake GitHub stars, risky dependencies and licence traps (github.com/m-ahmed-elbeskeri)

122 points

a year ago

633.

Show HN: Patchwork – Open-source framework to automate development gruntwork (github.com/patched-codes)

116 points

2 years ago

634.

Launch HN: LlamaFarm (YC W22) – Open-source framework for distributed AI (github.com/llama-farm)

106 points

8 months ago

635.

Show HN: Improve LLM Performance by Maximizing Iterative Development (github.com/palico-ai)

104 points

2 years ago

636.

Launch HN: Grai (YC S22) – Open-Source Data Observability Platform

101 points

ersatz_username

3 years ago

637.

Show HN: Dittofeed – 1-Click deploy, self-host Mailchimp alternative (github.com/dittofeed)

100 points

3 years ago

638.

Show HN: Index – New Open Source browser agent (github.com/lmnr-ai)

98 points

a year ago

639.

Show HN: Context Gateway – Compress agent context before it hits the LLM (github.com/Compresr-ai)

97 points

3 months ago

640.

Show HN: Nomadic – Minimize RAG Hallucinations with 1 Hyperparameter Experiment

95 points

2 years ago

641.

Show HN: Burr – A framework for building and debugging GenAI apps faster (github.com/DAGWorks-Inc)

94 points

2 years ago

642.

Show HN: What if your synthesizer was powered by APL (or a dumb K clone)? (octetta.github.io)

92 points

3 months ago

643.

Show HN: Gambit, an open-source agent harness for building reliable AI agents (github.com/bolt-foundry)

91 points

5 months ago

644.

Launch HN: Plexe (YC X25) – Build production-grade ML models from prompts (plexe.ai)

85 points

7 months ago

645.

Show HN: I open-sourced my Go and Next B2B SaaS Starter (deploy anywhere, MIT) (github.com/moasq)

83 points

6 months ago

646.

Show HN: Mcp-Agent – Build effective agents with Model Context Protocol (github.com/lastmile-ai)

80 points

a year ago

647.

Show HN: finetune LLMs via the Finetuning Hub (github.com/georgian-io)

80 points

3 years ago

648.

Show HN: FiddleCube – Generate Q&A to test your LLM (github.com/fiddlecube)

78 points

2 years ago

649.

Show HN: Infracost (YC W21): Cloud Costs for Terraform in VSCode

76 points

4 years ago

650.

Show HN: Torrix, self hosted, LLM Observability,(no Postgres, no Redis) (github.com/torrix-ai)

74 points

a month ago

651.

Launch HN: Cyberdesk (YC S25) – Automate Windows legacy desktop apps

73 points

10 months ago

652.

Show HN: EuConform – Offline-first EU AI Act compliance tool (open source) (github.com/Hiepler)

71 points

5 months ago

653.

Show HN: SpRAG – Open-source RAG implementation for challenging real-world tasks (github.com/SuperpoweredAI)

69 points

2 years ago

654.

Show HN: Kalosm an embeddable framework for pre-trained models in Rust (floneum.com)

66 points

2 years ago

655.

Show HN: Open-source model and scorecard for measuring hallucinations in LLMs (vectara.com)

65 points

3 years ago

656.

Show HN: OpenDataCapture an electronic data capture platform for data collection (github.com/DouglasNeuroInformatics)

61 points

2 years ago

657.

Show HN: Phospho – Text Analytics for LLM Apps (Posthog for Prompts) (github.com/phospho-app)

59 points

2 years ago

658.

Show HN: HyprMCP – Analytics, logs and auth for MCP servers (github.com/hyprmcp)

59 points

8 months ago

659.

Show HN: Vicinity – Fast, Lightweight Nearest Neighbors with Flexible Back Ends (github.com/MinishLab)

57 points

2 years ago

660.

Show HN: Betting game puzzle (Hamming neighbor sum in linear time)

56 points

a year ago