hallucination — salud del software de código abierto

Go · PyPI

86Excelenteíndice de salud

Self-hosted memory + evidence layer for AI agents (Claude Code, Codex, Hermes, ...) — embeddable Go library, MCP / HTTP / CLI, evidence-backed claims, bitemporal recall, axi-go execution kernel with JSONL audit + token budgets, cosign-signed releases with SLSA L3 provenance. No vendor cloud, no per-call billing.

Go★ 316 jul 2026

MIT16 jul 2026 · métricas 2.10.0

npm · crates.io

83Excelenteíndice de salud

silverstein/minutes

Every meeting, every idea, every voice note — searchable by your AI. Open-source, privacy-first conversation memory layer.

Rust★ 1372↓ 5342/mes23 jul 2026

MIT23 jul 2026 · métricas 2.10.0

npm · crates.io

65Buenoíndice de salud

Harmitx7/tribunal-kit

Anti-hallucination AI agent kit for Cursor, Windsurf & Antigravity. 27 specialist agents, 17 slash commands, 8 Tribunal reviewers. Install: npx tribunal-kit init

JavaScript · Python★ 3↓ 4637/mes19 jul 2026

MIT19 jul 2026 · métricas 2.10.0

npm · PyPI · crates.io +1

62Moderadoíndice de salud

muthuishere/citenexus

Evidence-first, multilingual, S3-native RAG — answers only from cited evidence (exact quote, page, bbox) and abstains when the evidence is weak, missing or conflicting. The guarantee is "no ungrounded claim". Byte-identical core across Python, Go and JavaScript. Docs: https://muthuishere.github.io/citenexus/

Python · Go · MDX★ 0↓ 665/mes5 sept 2026

MIT5 sept 2026 · métricas 2.10.0

npm

50Moderadoíndice de salud

LilMGenius/paperthin

Low-level agentic design patterns. Turning old engineering wisdom into reflexes your agent reaches for on its own—on any agent.

Shell · JavaScript★ 119↓ 4136/mes31 jul 2026

MIT31 jul 2026 · métricas 2.10.0

#hallucination