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
Provider-neutral control plane for durable-state agent swarms: subprocess workers, leases, artifacts, memory, and deterministic stitching.
2,6/gün ort. +1 son gün 133 commit 1 yazar Python 06 May 2026 güncellendi 10 gün önce - 2
Self-hosted coordination for AI workers: per-task graphs, device/model timelines, progress receipts, and source-aware usage. MIT.
1,4/gün ort. +0 son gün 6 commit 1 yazar Python 13 Ağu 2026 güncellendi 12 gün önce - 3
A dual-path memory system for proactive agents. Facts and procedures in a local knowledge graph, exposed as a CLI, MCP tools and skills. No
1/gün ort. +0 son gün — commit Python 06 Eyl 2026 güncellendi 02 Eki 2026 - 4
Let an LLM write its own tools at runtime: parsed with acorn, versioned in SQLite, run in a supervised worker process
0,4/gün ort. +0 son gün — commit TypeScript 11 Eyl 2026 güncellendi 12 Eyl 2026 - 5
SkillRoute by JEStats — local-first skill routing for coding agents, with ranked matches, confidence, and evidence over MCP.
0,3/gün ort. +0 son gün — commit Python 25 Haz 2026 güncellendi 5 gün önce - 6
A locally-running multi-agent human in the loop system for deep, interdisciplinary research with only 4 dependencies.
0,3/gün ort. +0 son gün — commit Python 31 Mar 2026 güncellendi 07 May 2026 - 7
🛠️ toolhub - Turn ANY console script into an LLM tool in 2 seconds. Lightweight, self-hosted, tree-structured alternative to MCP & LangChain
0,3/gün ort. +0 son gün — commit TypeScript 06 Eyl 2026 güncellendi 08 Eyl 2026 - 8
Evidence-driven skill evolution for Hermes Agent — reports, dry-run proposals, candidate search, and guarded apply
0,3/gün ort. +0 son gün — commit Python 03 May 2026 güncellendi 03 Eki 2026 - 9
memweave is a zero-infrastructure, async-first Python library that gives AI agents persistent, searchable memory — stored as plain Markdown
0,2/gün ort. +0 son gün — commit Python 22 Mar 2026 güncellendi 10 May 2026 - 10
Local-first AI bookmark manager with semantic search, cleanup review, Chrome sync-back, and MCP support.
0,1/gün ort. +0 son gün — commit TypeScript 26 Nis 2026 güncellendi 14 Haz 2026 - 11
🦄 Forge - a local-first, multi-agent software-engineering runtime that runs Claude Code / Codex-style agentic workflows entirely on your own
0,1/gün ort. +0 son gün — commit TypeScript 20 Nis 2026 güncellendi 27 Eyl 2026 - 12
Persistent, queryable memory for AI agents with intake policy, smart recall, context packs, graph recall, and multi-agent scoping
0,1/gün ort. +0 son gün — commit TypeScript 23 Nis 2026 güncellendi 31 Ağu 2026 - 13
Zero-infrastructure, local-first memory for AI agents. One SQLite file — no Postgres, Neo4j, or cloud. Bi-temporal supersession (updates, ne
0,1/gün ort. +0 son gün — commit JavaScript 15 Haz 2026 güncellendi 27 Eyl 2026