Havuz
Takip ettiğimiz konularda yükselen açık kaynak projeler — yıldız ivmesi, gerçek geliştirme aktivitesi ve AI değerlendirmesiyle.
Yalnız hareketli, son 28 günde commit almamış repoları gizler (yıldızı olan ama bırakılmış projeler). Commit sayısı henüz ölçülmemiş repolar da gizlenir.
EtiketTüm GitHub etiketleri — repo sahiplerinin koyduğu topic'lergöster
Etiketler yükleniyor…
- 1
Evidence-chain whiteboard + MCP server for AI research agents: every claim traces back to the run and code that produced it. 讓 AI agent 做研究時
33,2/gün ort. +9 son gün 12 commit 1 yazar JavaScript 26 Eki 2026 güncellendi 3 gün önce - 2
Tamper-evident tracing, policy gates and cross-checks for AI agents: see what the agent did, and why.
13,6/gün ort. +25 son gün 1.095 commit 21 yazar Python 26 Eyl 2026 güncellendi bugün - 3
The black box for AI-written code. Passive decision graph linking every commit to the agent prompts behind it: drift detection, DLP audit of
2,2/gün ort. -5 son gün 10 commit 2 yazar Rust 02 Tem 2026 güncellendi 10 gün önce - 4
Minimal Ed25519-signed activity receipts for verifiable AI agents — self-attested, offline-verifiable, no blockchain.
1,1/gün ort. +0 son gün — commit JavaScript 26 Eyl 2026 güncellendi 27 gün önce - 5
Lossless, local, provable memory for AI agents: every Claude Code session kept on your own computer, word for word, compressed and sealed, a
1/gün ort. +0 son gün — commit 12 Eki 2026 güncellendi dün - 6
A local-first coding agent that doesn't take "done" on faith: the engine keeps the run going until the project's own tests pass, and every g
0,6/gün ort. +0 son gün — commit TypeScript 04 Tem 2026 güncellendi 23 Eyl 2026 - 7
Cairn.ink Memory: lightweight cross-session memory for AI agents, with receipts.
0,6/gün ort. +0 son gün — commit JavaScript 04 Eyl 2026 güncellendi bugün - 8
A scientific-method runtime for AI agents: hypotheses, experiments, evidence, provenance, reproducibility, and auditable conclusions.
0,6/gün ort. +0 son gün — commit Python 02 Eki 2026 güncellendi dün - 9
Provenance-aware runtime security for AI agents with deterministic ALLOW / REVIEW / BLOCK enforcement.
0,5/gün ort. -4 son gün — commit Python 18 Ağu 2026 güncellendi 19 Ağu 2026 - 10
the governed runtime for agent skill workflows, off the leash but on the record
0,5/gün ort. +0 son gün — commit Rust 11 Nis 2026 güncellendi dün - 11
Agentic GraphRAG is an open source framework that builds a graph connecting your enterprise knowledge to the conversations your agents have
0,5/gün ort. +0 son gün — commit Python 20 Ağu 2026 güncellendi 4 gün önce - 12
Security-oriented three-axis observability for sandboxed AI agents: model intent, app context, and runtime telemetry into verifiable evidenc
0,4/gün ort. +0 son gün — commit Go 10 Haz 2026 güncellendi bugün - 13
Version control for AI agent memory. Commit, branch, merge, blame and time-travel what your agents know.
0,3/gün ort. +0 son gün — commit Rust 06 Eyl 2026 güncellendi dün - 14
Local-first verification layer for AI agents: evidence, provenance, policy gates, human approval, and auditable Trust Receipts before a clai
0,3/gün ort. +0 son gün — commit JavaScript 14 Tem 2026 güncellendi bugün - 15
AI agents should not make irreversible changes. TraceFold escrows the inverse before an effect lands, or refuses it, and issues receipts any
0,2/gün ort. +0 son gün — commit Rust 13 Ağu 2026 güncellendi 04 Eyl 2026 - 16
Extracts claims from SOPs, policies and regulations, has a person approve or reject each one, then serves the approved set to agents over MC
0,2/gün ort. +0 son gün — commit Rust 25 Ağu 2026 güncellendi 28 gün önce - 17
Relational codebase compiler and spec-driven containment engine for AI coding agents. Compiles polyglot repos (Rust, Python, TS, Go, C/C++,
0,2/gün ort. +0 son gün — commit Rust 24 Haz 2026 güncellendi dün - 18
Test what AI watermark and provenance evidence exists, whether it verifies, and what survives publishing.
0,2/gün ort. +1 son gün — commit Python 13 Ağu 2026 güncellendi 14 Ağu 2026 - 19
Decision provenance and data-flow tracking for coding agents: computes what changed in your code and data, records why it changed, and surfa
0,2/gün ort. +0 son gün — commit Python 16 Haz 2026 güncellendi 13 gün önce - 20
Self-hosted AI agent memory server with MCP, evidence provenance, typed claims, conflict detection, embeddings, recall, PostgreSQL, and pgve
0,2/gün ort. +0 son gün — commit Go 13 Nis 2026 güncellendi bugün - 21
Agent memory that needs no API key, no LLM, and no embedding provider. One command on Bun and it is serving MCP over stdio against a local S
0,2/gün ort. +0 son gün — commit TypeScript 29 Tem 2026 güncellendi bugün - 22
Permanent code intelligence layer. Learns what matters, expires what changed, proves what existed. Content-addressed graph with Merkle proof
0,1/gün ort. +0 son gün — commit Go 15 May 2026 güncellendi 29 Eyl 2026 - 23
FinishUP — local-first structured work evidence, deterministic checks, and honest verification receipts.
0,1/gün ort. +0 son gün — commit Python 13 Tem 2026 güncellendi dün - 24
WAKE.md for AI agents: compile project state so agents stop starting cold.
0,1/gün ort. +0 son gün — commit Python 17 May 2026 güncellendi 26 Tem 2026 - 25
Open-source MCP server over a git-backed Obsidian vault. Single-user, self-host. Six tools, hybrid search, provenance/blame, auto-link disco
0,1/gün ort. +0 son gün — commit TypeScript 01 Nis 2026 güncellendi 7 gün önce - 26
Governed knowledge bases that humans and AI agents write together: append-only, bitemporal, conflict-aware.
0,1/gün ort. +0 son gün — commit Python 24 Haz 2026 güncellendi bugün