bug-bounty480
google297
xss277
microsoft249
facebook211
rce159
apple150
exploit136
bragging-post102
account-takeover98
malware94
csrf84
cve79
privilege-escalation74
authentication-bypass65
stored-xss65
writeup61
reflected-xss57
browser54
react53
ssrf51
phishing50
dos50
input-validation49
cloudflare49
access-control49
cross-site-scripting48
node46
aws46
smart-contract45
docker45
sql-injection45
ethereum44
defi43
web-security43
web-application42
supply-chain42
oauth41
web339
burp-suite36
lfi34
vulnerability-disclosure34
idor34
html-injection33
smart-contract-vulnerability32
race-condition32
clickjacking31
reverse-engineering31
information-disclosure30
csp-bypass30
0
3/10
Tarvos introduces a relay architecture for AI coding agents that mitigates LLM context degradation by dispatching fresh agents sequentially, each reading a static master plan and receiving only a minimal 40-line handoff note, with automatic token-based switching when context budgets are exceeded.
ai-coding-agents
llm-optimization
context-window-management
relay-architecture
prompt-engineering
autonomous-development
token-tracking
claude-api
Tarvos
Claude Code
Chroma Research
MIT
0
2/10
Claude Forge is an adversarial pipeline using five Claude Code agents in generator/discriminator loops (Planner, Plan Reviewer, Implementer, Code Reviewer, Final Reviewer) to improve code correctness through iterative feedback and review cycles, trading 3x tokens and time for higher quality outputs.
ai-assisted-development
code-generation
llm-engineering
adversarial-pipeline
claude-api
code-review-automation
gan-inspired
prompt-engineering
test-driven-development
multi-agent-systems
Claude
Claude Forge
Claude Code