Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Login
Top
New
Best
Ask
Show
Jobs
931.
▲
Show HN: VectorLens – See why your RAG hallucinates, no config
1 point
gustav-proxi
3 months ago
discuss
932.
▲
Show HN: Wa-agent – Framework for building AI agents on WhatsApp
(github.com/ibrahimhajjaj)
1 point
ibrahimwithi
3 months ago
discuss
933.
▲
Show HN: Think Better – 155 decision-science rules for your AI assistant
(github.com/HoangTheQuyen)
1 point
hoangthequyen01
3 months ago
discuss
934.
▲
Show HN: Micro Chat: Group Chat with AI
(github.com/micro)
1 point
asim
3 months ago
discuss
935.
▲
Show HN: Single-header C++ libraries for LLM APIs – zero deps beyond libcurl
1 point
Shmungus
3 months ago
discuss
936.
▲
Show HN: Evalcraft – cassette-based testing for AI agents (pytest, $0/run)
(github.com/beyhangl)
1 point
beyhang
3 months ago
discuss
937.
▲
Show HN: OmniMon v4 – A cross-platform system monitor in Rust/Tauri (35MB RAM)
(github.com/chochy2001)
1 point
chochy2001
3 months ago
discuss
938.
▲
Show HN: KarnEvil9, a deterministic AI agent runtime
(github.com/oldeucryptoboi)
1 point
oldeucryptoboi
3 months ago
discuss
939.
▲
Show HN: Costrace – Open-source LLM cost and latency tracking across providers
(costrace.dev)
1 point
Ikotun
3 months ago
discuss
940.
▲
Show HN: Open-sourced AI Agent runtime (YAML-first)
(github.com/NikoSokratous)
1 point
nsokra02
3 months ago
discuss
941.
▲
Show HN: Llmdoc – annotate codebase with LLM summaries only re-scan what changed
(github.com/tristanMatthias)
1 point
tristanMatthias
3 months ago
discuss
942.
▲
Show HN: Epstein-Search – Local, AI-Powered Search Engine for the Epstein Files
(github.com/simulationship)
1 point
simulationship
3 months ago
discuss
943.
▲
Show HN: Prompt-run – run .prompt files against any LLM from the terminal
(github.com/Maneesh-Relanto)
1 point
maneeshthakur
3 months ago
discuss
944.
▲
Show HN: AgentWeb – Free business directory API for AI agents (11M+ businesses)
(agentweb.live)
1 point
ReidarO
3 months ago
discuss
945.
▲
Show HN: Anonymize LLM traffic to dodge API fingerprinting and rate-limiting
(github.com/xinxin7)
1 point
clawshield
3 months ago
discuss
946.
▲
Show HN: AgentKeeper – Cross-model memory for AI agents
(github.com/tomanciauxberner-rgb)
1 point
thinklanceai
3 months ago
discuss
947.
▲
Show HN: Prompt2pwn – CTF Automated Solver
(github.com/edelauna)
1 point
bigEnotation
3 months ago
discuss
948.
▲
Show HN: Neuron – Independent Rust crates for building AI agents
(secbear.github.io)
1 point
secbear
4 months ago
discuss
949.
▲
Show HN: Tacit – The missing Layer 3 of the AI agent stack (open source)
(github.com/tacitprotocol)
1 point
ms170888
4 months ago
discuss
950.
▲
Show HN: Jsonchunk – Parse incomplete JSON from streaming LLM responses
(github.com/jbingen)
1 point
jbingen
4 months ago
discuss
951.
▲
Show HN: VerdictMail
(github.com/ascarola)
1 point
ascarola
4 months ago
discuss
952.
▲
I spent $100 benchmarking LLM providers on a weekend CTF
1 point
wwdmaxwell
4 months ago
discuss
953.
▲
Show HN: SpecterQA – AI personas test your web app, no scripts needed
1 point
synctek
4 months ago
discuss
954.
▲
Show HN: Attest – Test AI agents with 8-layer graduated assertions
1 point
tommathews
4 months ago
discuss
955.
▲
Show HN: Code Lantern– A self-hosted, local code-analysis and visualization tool
(github.com/Tjindl)
1 point
tjindl
4 months ago
discuss
956.
▲
Show HN: Xpaper – A Chrome extension to turn your X feed into a newsletter
(github.com/laiso)
1 point
laiso
4 months ago
discuss
957.
▲
Show HN: Expectllm – "expect"-style pattern matching for LLM conversations
(github.com/entropyvector)
1 point
entropyvector
4 months ago
discuss
958.
▲
Show HN: oMLX – Native Mac inference server that persists KV cache to SSD
(github.com/jundot)
1 point
jundot
4 months ago
discuss
959.
▲
Show HN: Treliq – PR triage CLI with 20 signals and optional LLM scoring
(github.com/mahsumaktas)
1 point
chrismagno
4 months ago
discuss
960.
▲
Show HN: AgentDX – Open-source linter and LLM benchmark for MCP servers
(github.com/agentdx)
1 point
yamarldfst
4 months ago
discuss
More