HK
Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Top
New
Best
Ask
Show
Jobs
Request
121.
▲
Precision-Based Sampling of LLM Judges
sunnybak.net
discuss
a year ago
sunny-bak
1 points
122.
▲
Show HN: Lone Arena – Self-hosted LLM human evaluation, you be the judge
github.com/Contextualist
discuss
2 years ago
Contextualist
1 points
123.
▲
Collection of TypeScript type challenges with online judge
github.com/type-challenges
discuss
2 years ago
max-m
1 points
124.
▲
Show HN: Covid-19 Derived Datasets (JHU, NY Times, ECDC) in JSON, TSV, SQL
github.com/cipriancraciun
discuss
6 years ago
ciprian_craciun
1 points
125.
▲
Open issues waiting for response on Novel Covid-19 Cases – JHU CSSE
github.com/CSSEGISandData
discuss
6 years ago
tonycletus
1 points
126.
▲
Show HN: A self hosted online judge for meetups and workshops, written in Go
github.com/MohamedBassem
discuss
9 years ago
mohamedbassem
1 points
127.
▲
Show HN: My Single-File Python Script I Used to Replace Splunk in My Startup
github.com/Dicklesworthstone
79 comments
3 years ago
eigenvalue
313 points
128.
▲
Show HN: A Karpathy-style LLM wiki your agents maintain (Markdown and Git)
github.com/nex-crm
115 comments
2 months ago
najmuzzaman
260 points
129.
▲
Show HN: Minimal, self-hosted exercise tracker
github.com/bmtwl
39 comments
a year ago
DrPhish
127 points
130.
▲
Show HN: Terminal-Bench-RL: Training long-horizon terminal agents with RL
github.com/Danau5tin
12 comments
a year ago
Danau5tin
125 points
131.
▲
Launch HN: Confident AI (YC W25) – Open-source evaluation framework for LLM apps
27 comments
a year ago
jeffreyip
117 points
132.
▲
Show HN: SirixDB – Bitemporal binary JSON database system and event store
github.com/sirixdb
16 comments
3 years ago
lichtenberger
109 points
133.
▲
Launch HN: Traceloop (YC W23) – Detecting LLM Hallucinations with OpenTelemetry
72 comments
2 years ago
GalKlm
101 points
134.
▲
Show HN: Index – New Open Source browser agent
github.com/lmnr-ai
45 comments
a year ago
skull8888888
98 points
135.
▲
Show HN: RULER – Easily apply RL to any agent
openpipe.ai
11 comments
a year ago
kcorbitt
81 points
136.
▲
Show HN: Torrix, self hosted, LLM Observability,(no Postgres, no Redis)
github.com/torrix-ai
4 comments
a month ago
AdarshRao23
74 points
137.
▲
Show HN: OCR Benchmark Focusing on Automation
nanonets.com
21 comments
a year ago
prats226
58 points
138.
▲
Show HN: Cap'n-rs – Rust implementation of Cloudflare's Cap'n Web protocol
github.com/currentspace
35 comments
9 months ago
brian_meek
52 points
139.
▲
Show HN: TensorZero – open-source data and learning flywheel for LLMs
github.com/tensorzero
2 comments
2 years ago
GabrielBianconi
49 points
140.
▲
Show HN: Helicone (YC W23) – OSS LLM Observability and Development Platform
github.com/Helicone
7 comments
a year ago
justintorre75
29 points
141.
▲
Show HN: Create LLM graders and run evals in JavaScript with one file
github.com/bolt-foundry
2 comments
a year ago
randall
28 points
142.
▲
Show HN: FutureSearch – answer hard questions like "Who will buy TikTok US?"
3 comments
2 years ago
ddp26
22 points
143.
▲
Show HN: OSS sustain guard – Sustainability signals for OSS dependencies
onukura.github.io
6 comments
6 months ago
onukura
21 points
144.
▲
Show HN: Anytype – a local and collaborative database with API and MCP server
zhanna.any.org
discuss
a year ago
sharipova
20 points
145.
▲
Show HN: I built an open-source AI data layer that connects any LLM to any data
github.com/bagofwords1
3 comments
9 months ago
y14
18 points
146.
▲
Show HN: TinyFish Web Agent (82% on hard tasks vs. Operator's 43%)
tinyfish.ai
12 comments
4 months ago
gargi_tinyfish
17 points
147.
▲
Show HN: Meta-agent: self-improving agent harnesses from live traces
github.com/canvas-org
discuss
3 months ago
essamsleiman
14 points
148.
▲
Ask HN: Help me improve my C-like language, C3
7 comments
6 years ago
Nuoji
12 points
149.
▲
Show HN: Ebiose – A Darwin‑Style Playground for Self‑Evolving AI Agents
github.com/ebiose-ai
3 comments
a year ago
vincent-ebiose
12 points
150.
▲
Show HN: OpenTiger – Autonomous dev orchestration that never stops
github.com/Andyyyy64
2 comments
4 months ago
andyyyy64
11 points
More